{"id":307513,"date":"2024-09-03T14:47:58","date_gmt":"2024-09-03T14:47:58","guid":{"rendered":"https:\/\/www.techopedia.com\/?p=307513"},"modified":"2024-09-12T09:52:31","modified_gmt":"2024-09-12T09:52:31","slug":"ibm-ntt-explain-how-ai-works-on-edge-computing","status":"publish","type":"post","link":"https:\/\/www.techopedia.com\/ibm-ntt-explain-how-ai-works-on-edge-computing","title":{"rendered":"IBM &#038; NTT Data Explain How AI Works on Edge Computing"},"content":{"rendered":"<p>One trillion plus AI <a href=\"https:\/\/www.techopedia.com\/experts\/what-is-the-role-of-parameters-in-ai\">parameter models<\/a> are already banging hard at our front door. These new <a href=\"https:\/\/www.techopedia.com\/definition\/190\/artificial-intelligence-ai\">artificial intelligence<\/a> models, with unprecedented computing power, will become the norm in the coming months and years ahead.<\/p>\n<p>While the technological advancements of new <a href=\"https:\/\/www.techopedia.com\/definition\/34633\/generative-ai\">generative AI<\/a> models are promising and expected to benefit most sectors and industries, the world still has a big AI-size-edge-infrastructure problem (we will break this down in a moment).<\/p>\n<p>How will giant AI models operate on the <a href=\"https:\/\/www.techopedia.com\/definition\/32472\/edge-computing\">edge<\/a> of networks while offering low <a href=\"https:\/\/www.techopedia.com\/definition\/2228\/latency\">latency<\/a> and real-time services? It&#8217;s a &#8216;shrinking giant&#8217; problem.<\/p>\n<p>In this report, Techopedia talks with NTT Data and IBM experts to understand an approach to solving fast, resource-intensive <a href=\"https:\/\/www.techopedia.com\/definition\/190\/artificial-intelligence-ai\">artificial intelligence<\/a> without over-burdening a network.<\/p>\n<div class=\"su-note\"  style=\"border-color:#dddddd;border-radius:3px;-moz-border-radius:3px;-webkit-border-radius:3px;\"><div class=\"su-note-inner su-u-clearfix su-u-trim\" style=\"background-color:#f7f7f7;border-color:#ffffff;color:#333333;border-radius:3px;-moz-border-radius:3px;-webkit-border-radius:3px;\">\n<h2><span id=\"key_takeaways\">Key Takeaways<\/span><\/h2>\n<ul>\n<li>Large AI models are often too resource-intensive for edge devices.<\/li>\n<li>Smaller, more efficient AI models offer a practical solution for deploying AI at the edge.<\/li>\n<li>Industries such as manufacturing need AI solutions that can operate effectively in distributed environments.<\/li>\n<li>Successful edge AI deployment requires collaboration between silos of information, and it is beginning to happen today.<\/li>\n<\/ul>\n<\/div><\/div>\n<div>\n    <section class=\"toc-sticky w-100 bg-white \">\n        <div class=\"toc-sticky__container container\">\n            <div class=\"toc-sticky__open d-flex align-items-end\" data-bs-toggle=\"collapse\"\n                 aria-controls=\"multiCollapse1\"\n                 data-bs-target=\"#multiCollapse1\">\n                <button\n                        class=\"btn btn-primary collapse-action-btn p-1 rounded-circle\"\n                        type=\"button\"\n                >\n                    <i class=\"icon-chevron-up\"><\/i>\n                <\/button>\n                <span id=\"toc-current-title\" class=\"d-flex align-items-center\">\n                    Table of Contents\n                <\/span>\n                <span class=\"toc-main-title-permanent\">Table of Contents<\/span>\n            <\/div>\n            <div\n                    class=\"collapse my-3\"\n                    id=\"multiCollapse1\"\n            >\n                <ol class=\"StepProgress\">\n                                                                        <li class=\"StepProgress-item current\">\n                                                <div class=\"StepProgress-item__group\">\n                            <a data-id=\"key_takeaways\"\n                               onclick=handleScrollToTitle(\"key_takeaways\")\n                               class=\"StepProgress-item__link\" data-level=\"2\">Key Takeaways<\/a>\n                                                    <\/div>\n                                                <\/li>\n                                                                        <li class=\"StepProgress-item\">\n                                                <div class=\"StepProgress-item__group\">\n                            <a data-id=\"is_the_solution_an_edge_infrastructure_combined_with_smaller_ai_models\"\n                               onclick=handleScrollToTitle(\"is_the_solution_an_edge_infrastructure_combined_with_smaller_ai_models\")\n                               class=\"StepProgress-item__link\" data-level=\"2\">Is the Solution an Edge Infrastructure Combined with Smaller AI Models?<\/a>\n                                                    <\/div>\n                                                <\/li>\n                                                                        <li class=\"StepProgress-item\">\n                                                <div class=\"StepProgress-item__group\">\n                            <a data-id=\"speaking_the_many_languages_of_edge_computing\"\n                               onclick=handleScrollToTitle(\"speaking_the_many_languages_of_edge_computing\")\n                               class=\"StepProgress-item__link\" data-level=\"2\">Speaking the Many Languages of Edge Computing<\/a>\n                                                    <\/div>\n                                                <\/li>\n                                                                        <li class=\"StepProgress-item\">\n                                                <div class=\"StepProgress-item__group\">\n                            <a data-id=\"an_ai_built_for_your_edge\"\n                               onclick=handleScrollToTitle(\"an_ai_built_for_your_edge\")\n                               class=\"StepProgress-item__link\" data-level=\"2\">An AI Built for Your Edge<\/a>\n                                                    <\/div>\n                                                <\/li>\n                                                                        <li class=\"StepProgress-item\">\n                                                <div class=\"StepProgress-item__group\">\n                            <a data-id=\"the_bottom_line\"\n                               onclick=handleScrollToTitle(\"the_bottom_line\")\n                               class=\"StepProgress-item__link\" data-level=\"2\">The Bottom Line<\/a>\n                                                    <\/div>\n                                                <\/li>\n                                                                        <li class=\"StepProgress-item\">\n                                                <div class=\"StepProgress-item__group\">\n                            <a data-id=\"references\"\n                               onclick=handleScrollToTitle(\"references\")\n                               class=\"StepProgress-item__link\" data-level=\"2\">References<\/a>\n                                                    <\/div>\n                                                <\/li>\n                                    <\/ol>\n                <div class=\"toc-sticky__container__disperse\"><\/div>\n                <div class=\"toc-sticky__btn-top justify-content-center\">\n                    <button class=\"btn btn-link d-flex align-items-center\" onclick={btnTop()}><p>Show Full Guide<\/p><img decoding=\"async\"\n                                src=\"\/wp-content\/plugins\/table-of-contents\/assets\/images\/arrow-up-circle.svg\"\n                                alt=\"arrow-up-circle\">\n                    <\/button>\n                <\/div>\n            <\/div>\n        <\/div>\n    <\/section>\n    <div class=\"toc-sticky-list\">\n        <div class=\"toc-sticky__container container\">\n            <div class=\"toc-sticky__open d-flex align-items-end\" data-bs-toggle=\"collapse\" aria-controls=\"multiCollapse2\" data-bs-target=\"#multiCollapse2\">\n                <button class=\"btn btn-primary collapse-action-btn p-1 rounded-circle\"\n                        type=\"button\">\n                    <i class=\"icon-chevron-up up\"><\/i>\n                <\/button>\n                <span id=\"toc-current-title\" class=\"d-flex align-items-center\">\n                    Table of Contents\n                <\/span>\n            <\/div>\n            <div  class=\"collapse my-3\" id=\"multiCollapse2\">\n                <ol class=\"StepProgress\">\n                    \t\t\t\t\t \t\t\t\t\t                                                     <li class=\"StepProgress-item current \">\n                                                    <div class=\"StepProgress-item__group\">\n                                <a data-id=\"key_takeaways\"\n                                   onclick=handleScrollToTitle(\"key_takeaways\")\n                                   class=\"StepProgress-item__link\"\n                                   data-level=\"2\">Key Takeaways<\/a>\n                                                            <\/div>\n                                                    <\/li>\n                    \t\t\t\t\t \t\t\t\t\t                                                     <li class=\"StepProgress-item \">\n                                                    <div class=\"StepProgress-item__group\">\n                                <a data-id=\"is_the_solution_an_edge_infrastructure_combined_with_smaller_ai_models\"\n                                   onclick=handleScrollToTitle(\"is_the_solution_an_edge_infrastructure_combined_with_smaller_ai_models\")\n                                   class=\"StepProgress-item__link\"\n                                   data-level=\"2\">Is the Solution an Edge Infrastructure Combined with Smaller AI Models?<\/a>\n                                                            <\/div>\n                                                    <\/li>\n                    \t\t\t\t\t \t\t\t\t\t                                                     <li class=\"StepProgress-item \">\n                                                    <div class=\"StepProgress-item__group\">\n                                <a data-id=\"speaking_the_many_languages_of_edge_computing\"\n                                   onclick=handleScrollToTitle(\"speaking_the_many_languages_of_edge_computing\")\n                                   class=\"StepProgress-item__link\"\n                                   data-level=\"2\">Speaking the Many Languages of Edge Computing<\/a>\n                                                            <\/div>\n                                                    <\/li>\n                    \t\t\t\t\t \t\t\t\t\t\n\t\t\t\t\t\t <span class=\"show_moretoc\">Show Full Guide<\/span>\n\t\t\t\t\t\t \t\t\t\t\t \t\t\t\t\t\t  \t\t\t\t\t                                                      <li class=\"StepProgress-item ms_hidetoc\">\n                                                    <div class=\"StepProgress-item__group\">\n                                <a data-id=\"an_ai_built_for_your_edge\"\n                                   onclick=handleScrollToTitle(\"an_ai_built_for_your_edge\")\n                                   class=\"StepProgress-item__link\"\n                                   data-level=\"2\">An AI Built for Your Edge<\/a>\n                                                            <\/div>\n                                                    <\/li>\n                    \t\t\t\t\t \t\t\t\t\t \t\t\t\t\t\t  \t\t\t\t\t                                                      <li class=\"StepProgress-item ms_hidetoc\">\n                                                    <div class=\"StepProgress-item__group\">\n                                <a data-id=\"the_bottom_line\"\n                                   onclick=handleScrollToTitle(\"the_bottom_line\")\n                                   class=\"StepProgress-item__link\"\n                                   data-level=\"2\">The Bottom Line<\/a>\n                                                            <\/div>\n                                                    <\/li>\n                    \t\t\t\t\t \t\t\t\t\t \t\t\t\t\t\t  \t\t\t\t\t                                                      <li class=\"StepProgress-item ms_hidetoc\">\n                                                    <div class=\"StepProgress-item__group\">\n                                <a data-id=\"references\"\n                                   onclick=handleScrollToTitle(\"references\")\n                                   class=\"StepProgress-item__link\"\n                                   data-level=\"2\">References<\/a>\n                                                            <\/div>\n                                                    <\/li>\n                                    <\/ol>\n            <\/div>\n            <div class=\"toc-sticky__container__disperse\"><\/div>\n        <\/div>\n    <\/div>\n<\/div>\n\n<script id=\"toc-js\">\n    window.addEventListener(\"DOMContentLoaded\", () => {\n        const header = document.querySelector(\".header_wrapper\");\n\n        const pageLegend = document.querySelector('#multiCollapse1');\n        const pageLegendList = document.querySelector('#multiCollapse2');\n        const pageLegendCollapse = new bootstrap.Collapse(pageLegend, {toggle: document.querySelector(\".toc-sticky\").classList.contains('sticky')});\n\n        \/**\n         * Changing current title\n         *\/\n        (function (pageLegend) {\n            const titleNodes = pageLegend.querySelectorAll('.StepProgress-item__link');\n\n            if (!titleNodes.length) return;\n\n            const titles = [...titleNodes].map((itm, i) => ({\n                id: itm.getAttribute('data-id'),\n                text: itm.textContent,\n                level: itm.getAttribute('data-level'),\n                linkNode: itm,\n                titleNode: document.getElementById(itm.getAttribute('data-id')),\n                index: i,\n            }));\n\n            \/**\n             * Source: https:\/\/www.sitepoint.com\/throttle-scroll-events\/\n             * @param {Function} fn\n             * @param {number} wait\n             * @returns {(function(): void)|*}\n             *\/\n            const throttle = (fn, wait) => {\n                let time = Date.now();\n                return function () {\n                    if ((time + wait - Date.now()) < 0) {\n                        fn();\n                        time = Date.now();\n                    }\n                }\n            }\n\n            const changeCurrentTitle = () => {\n                const documentScrollTop = window.pageYOffset || document.documentElement.scrollTop || document.body.scrollTop || 0;\n                let current = 0;\n\n                \/\/ Title\n                titles.forEach((itm, i) => {\n\t\t\t\t\/\/console.log(itm)\n                    const itmOffsetTop = itm.titleNode ? itm.titleNode.offsetTop - 100 : 0;\n\n                    if (documentScrollTop >= itmOffsetTop) {\n                        document.getElementById('toc-current-title').innerHTML = itm.text;\n                        document.getElementById('toc-current-title').setAttribute('data-current-id', itm.id);\n                        document.getElementById('toc-current-title').setAttribute('data-current-level', itm.level);\n                        current = i;\n                    }\n                })\n\n                \/\/ close all list and open sub list if needed\n                if (document.querySelector(\".toc-sticky\").classList.contains('sticky')) {\n                    document.querySelectorAll('.subList-in-progress').forEach((el) => {\n                        el.children[1].classList.remove('show');\n                        el.getElementsByClassName('icon-chevron-down')[0].classList.remove('up');\n                    });\n                    const currentEl = titles[current];\n                    currentEl.linkNode.classList.add('show');\n                }\n\n                titles.forEach((itm, i) => {\n                    itm.linkNode.parentNode.parentNode.classList.remove('current', 'is-done');\n                    if (current > i) {\n                        itm.linkNode.parentNode.parentNode.classList.add('is-done')\n                    };\n                    if (current === i) {\n                      itm.linkNode.parentNode.parentNode.classList.add('current');\n                    };\n                })\n\n            }\n\n            changeCurrentTitle();\n\n            document.addEventListener('scroll', throttle(changeCurrentTitle, 50));\n        })(pageLegend);\n\n\n        \/**\n         *  Collapse\n         *\/\n        (function (pageLegend, header) {\n            const icon = pageLegend.parentNode.querySelector(\".collapse-action-btn i\");\n\n            const collapseToggle = (status) => (e) => {\n                if (!e.target.isEqualNode(pageLegend)) return;\n\n                icon.classList.toggle(\"up\");\n\n                const containerHeight = pageLegend.getBoundingClientRect().height;\n\n                const showSubtitleContent = () => {\n                    const currentId = document.getElementById('toc-current-title').getAttribute('data-current-id');\n                    const currentLevel = document.getElementById('toc-current-title').getAttribute('data-current-level');\n                    const currentSubTitle = currentLevel == 3 ? document.querySelector(`a[data-id=\"${currentId}\"]`).parentNode.parentNode.parentNode : false;\n\n                    if (!currentSubTitle) return;\n                    new bootstrap.Collapse(currentSubTitle, {toggle: false}).show();\n                }\n\n                showSubtitleContent();\n                if (status === 'shown' && document.querySelector(\".toc-sticky\").classList.contains('sticky') ) {\n                    document.querySelector('html').classList.remove('overflow-hidden');\n                    pageLegend.classList.add('overflow-auto');\n                    pageLegend.style.height = `calc(100vh - ${header.getBoundingClientRect().height + document.querySelector('.toc-sticky__open').getBoundingClientRect().height + 16}px)`;\n                } else if (status === 'hide') {\n                    document.querySelector('html').classList.remove('overflow-hidden');\n                    pageLegend.classList.remove('overflow-auto');\n                    pageLegend.style.height = 'auto';\n                }\n            }\n\n            pageLegend.addEventListener('shown.bs.collapse', collapseToggle('shown'));\n            pageLegend.addEventListener('hide.bs.collapse', collapseToggle('hide'));\n        })(pageLegend, header);\n\n        \/**\n         * Collapse sub-titles\n         *\/\n        (function (pageLegend) {\n            const collapseEls = pageLegend.querySelectorAll('.collapse');\n\n            collapseEls.forEach(function (el) {\n\n                const toggleArrowDirection = function (e) {\n                    if (!e.target.isEqualNode(el)) return;\n\n                    const id = this.getAttribute('id');\n                    document.querySelector(`.collapse-action-btn[data-bs-target=\"#${id}\"] .icon-chevron-down`).classList.toggle('up');\n                }\n                el.addEventListener('shown.bs.collapse', toggleArrowDirection);\n                el.addEventListener('hide.bs.collapse', toggleArrowDirection);\n            })\n        })(pageLegend);\n\n        \/**\n         *  Collapse main title\n         *\/\n        (function (pageLegendList) {\n            const icon = pageLegendList.parentNode.querySelector(\".collapse-action-btn i\");\n\n            const collapseToggle = () => (e) => {\n                if (!e.target.isEqualNode(pageLegendList)) return;\n\n                icon.classList.toggle(\"up\");\n\n            }\n            pageLegendList.addEventListener('shown.bs.collapse', collapseToggle());\n            pageLegendList.addEventListener('hide.bs.collapse', collapseToggle());\n        })(pageLegendList);\n\n        (function (pageLegendList) {\n            const collapseEls = pageLegendList.querySelectorAll('.collapse');\n\n            collapseEls.forEach(function (el) {\n\n                const toggleArrowDirection = function (e) {\n                    if (!e.target.isEqualNode(el)) return;\n\n                    const id = this.getAttribute('id');\n                    document.querySelector(`.toc-sticky-list .collapse-action-btn[data-bs-target=\"#${id}\"] .icon-chevron-down`).classList.toggle('up');\n                }\n                el.addEventListener('shown.bs.collapse', toggleArrowDirection);\n                el.addEventListener('hide.bs.collapse', toggleArrowDirection);\n            })\n        })(pageLegendList);\n\n        \/**\n         * Sticky functionality\n         * Source: https:\/\/stackoverflow.com\/questions\/17893771\/javascript-sticky-div-after-scroll\n         *\/\n        (function (header, pageLegendCollapse) {\n            \/\/ set everything outside the onscroll event (less work per scroll)\n            const target = document.querySelector(\".toc-sticky\");\n            const targetListStatic = document.querySelector(\".toc-sticky-list\");\n\n            if (!target || !header) return;\n\n            const headerHeight = header.getBoundingClientRect().height;\n            const targetHeight = targetListStatic.getBoundingClientRect().height;\n\n            \/\/ -headerHeight so it won't be jumpy\n            const stop = targetListStatic.offsetTop + headerHeight + targetHeight;\n            const docBody =\n                document.documentElement || document.body.parentNode || document.body;\n            const hasOffset = window.pageYOffset !== undefined;\n\n            const applySticky = function () {\n                \/\/ cross-browser compatible scrollTop.\n                const scrollTop = hasOffset ? window.pageYOffset : docBody.scrollTop;\n\n                \/\/ if user scrolls to headerHeight from the top of the target div\n                if (scrollTop >= stop) {\n                    pageLegendCollapse.hide();\n                    \/\/ stick the div\n                    target.classList.add(\"sticky\");\n                    \/\/target.style.marginTop = `${headerHeight}px`;\n                } else {\n                    pageLegendCollapse.show();\n                    \/\/ release the div\n                    target.classList.remove(\"sticky\");\n                    target.style.marginTop = \"\";\n                }\n            }\n\n            applySticky();\n\n            window.addEventListener('scroll', applySticky);\n        })(header, pageLegendCollapse);\n\tjQuery('span.show_moretoc').click(function(){\n\t\tjQuery('span.show_moretoc').hide();\n\t   jQuery('.ms_hidetoc').show();\n\t});\n    });\n\n    \/\/ When the user clicks on the button, scroll to the top of the document\n    function btnTop() {\n        const pageLegend = document.querySelector('#multiCollapse1');\n        document.querySelector('html').classList.remove('overflow-hidden');\n        pageLegend.classList.remove('overflow-auto');\n        pageLegend.style.height = 'auto';\n        window.scrollTo({\n            top: 0,\n            behavior: 'smooth'\n        });\n    }\n\n    const handleScrollToTitle = (id) => {\n        const el = document.getElementById(id);\n        const headerHeightDifference = window.innerWidth < 992 ? -30 : -15;\n        window.scrollTo({\n            top: el.offsetTop - 60 - headerHeightDifference - 10,\n        });\n    }\n<\/script>\n\n<h2><span id=\"is_the_solution_an_edge_infrastructure_combined_with_smaller_ai_models\">Is the Solution an Edge Infrastructure Combined with Smaller AI Models?<\/span><\/h2>\n<p>Compute power is rapidly moving from the <a href=\"https:\/\/www.techopedia.com\/definition\/349\/data-center\">data center<\/a> to the edge. Organizations expect edge computing <a href=\"https:\/\/www.redhat.com\/rhdc\/managed-files\/cl-451-research-on-edge-computing-analyst-material-1323765-202408-en.pdf\" target=\"_blank\">to significantly impact all aspects of operations<\/a>. Meanwhile, worldwide spending on edge computing is expected to be <a href=\"https:\/\/www.idc.com\/getdoc.jsp?containerId=prUS51960324\" target=\"_blank\">$232 billion in 2024<\/a>, an increase of 15.4% over 2023 \u2014 largely driven by AI.<\/p>\n<p>Techopedia spoke to <a href=\"https:\/\/www.linkedin.com\/in\/bloudoff\/\" target=\"_blank\"><strong>Paul Bloudoff<\/strong><\/a><strong>, Senior Director, Edge Services, <\/strong><a href=\"https:\/\/www.nttdata.com\/global\/en\/\" target=\"_blank\"><strong>NTT Data<\/strong><\/a>, which focuses on edge AI \u2014 particularly smaller, more efficient <a href=\"https:\/\/www.techopedia.com\/top-10-trustworthy-ai-models\">AI models<\/a>. These models are use-case specific and sized to be simple to deploy and run.<\/p>\n<blockquote><p>&#8220;When we look at bringing AI to the edge, we need to understand the business use case and what organizations are trying to accomplish. Not every deployment will need monolithic AI models to support real-life use cases.&#8221;<\/p><\/blockquote>\n<p>Bloudoff explained how IT and <a href=\"https:\/\/www.techopedia.com\/definition\/operational-technology-ot\">Operational Technology<\/a> (OT) teams can benefit from small AI models running on lightweight edge.<\/p>\n<p>For example, in factory floors, these AI solutions can enhance maintenance by breaking down siloes and bringing together a suite of information provided by the <a href=\"https:\/\/www.techopedia.com\/definition\/28247\/internet-of-things-iot\">Internet of Things<\/a> (IoT) to, for instance, track data on vibration, temperature, machine wear, and more.<\/p>\n<p>Industrial predictive maintenance AI <a href=\"https:\/\/iot-analytics.com\/predictive-maintenance-market\/\" target=\"_blank\">can save organizations thousands of dollars <\/a>by reducing downtime.<\/p>\n<blockquote><p>&#8220;To accomplish this (use case), organizations will not need a million-dollar AI platform to process this kind of information.<\/p>\n<p>&#8220;For many organizations, the resource investment to bring monolithic AI solutions to the edge is too complex and costly.&#8221;<\/p><\/blockquote>\n<p>Shrinking AI Giants into TinyAI to Drive Sustainable Development<\/p>\n<p>Scentistific researchers already <a href=\"https:\/\/www.sciencedirect.com\/science\/article\/abs\/pii\/S2666998624002473\" target=\"_blank\">advocate for TinyAI models<\/a> as the solution to the complex transition of data center AI models into edge computing.<\/p>\n<p>Scientists argue that TinyAI models can be deployed in healthcare, agriculture, and urban development and contribute to the development of the United Nations Sustainable Development Goals. Tiny models are designed for specific use cases and, therefore, are more cost-efficient, and consume less power, driving sustainability targets.<\/p>\n<p><a href=\"https:\/\/www.linkedin.com\/in\/nicholascmfuller\/\" target=\"_blank\"><strong>Nick Fuller<\/strong><\/a><strong>, Vice President of AI and Automation at <\/strong><a href=\"https:\/\/research.ibm.com\/\" target=\"_blank\"><strong>IBM Research<\/strong><\/a>, told Techopedia that for edge workloads requiring low latency, inferencing on devices is more than highly desirable; it is essential.<\/p>\n<blockquote><p>&#8220;To this end, serving &#8216;small&#8217; foundation models on such devices (robotic arms, mobile devices, cameras, etc.) facilitates on-device inferencing within the budget (memory, compute, accelerator) constraints of such devices.&#8221;<\/p><\/blockquote>\n<p>&#8220;Models, of course, can still be trained on-premise or on the <a href=\"https:\/\/www.techopedia.com\/definition\/2\/cloud-computing\">cloud<\/a>. To this end, lightweight AI models are very appealing to the edge market and especially to specific workloads where latency requirements are essential.&#8221;<\/p>\n<h2><span id=\"speaking_the_many_languages_of_edge_computing\">Speaking the Many Languages of Edge Computing<\/span><\/h2>\n<p>Many developers fear that edge infrastructure is constrained in terms of computing power processing, data storage, and memory. Tehcopedi asked Bloudoff from NTT Data how the company approached this problem.<\/p>\n<p>Bloudoff explained that one of the challenges organizations face when deploying solutions at the edge is the silos between machines and devices across their network \u2014 machines and devices from different manufacturers do not always communicate well with each other.<\/p>\n<p>&#8220;Think of it as different individuals speaking different languages who are all providing data that needs to be collected, analyzed, processed, and transformed into action,&#8221; Bloudoff said.<\/p>\n<p>&#8220;What&#8217;s powerful about an Edge AI platform is that its software layer automatically discovers devices and machines across an IT or OT environment through its smaller, more efficient language learning model,&#8221; Bloudoff added.<\/p>\n<p>NTT&#8217;s Edge AI platform runs auto-discovery and unifies and processes the data to provide a comprehensive diagnostic report that can be used for AI-powered solutions.<\/p>\n<blockquote><p>&#8220;Once you break down silos and connect with stakeholders across different teams, you will have a better understanding of your processing power and memory needs.<\/p>\n<p>&#8220;Bigger isn&#8217;t always better.&#8221;<\/p><\/blockquote>\n<p>Speaking to Techopedia, <strong>IBM Fellow <\/strong><a href=\"https:\/\/newsroom.ibm.com\/cait-crawford\" target=\"_blank\"><strong>Catherine Crawford<\/strong><\/a> added that the challenge is not just in how to move AI to the edge.<\/p>\n<p>&#8220;There are multiple existing use cases that can leverage edge using smaller AI models where the technical challenges still exist and assets can be developed for distributed, secure Edge to Cloud continuous development AIOps.&#8221;<\/p>\n<p>Crawford explained that there is ongoing interest and research in understanding how task-tuned, smaller genAI and <a href=\"https:\/\/www.techopedia.com\/definition\/34826\/foundation-model\">foundational models<\/a> can be developed and leveraged for edge use cases considering constraints like compute, memory, storage, and power (battery life).<\/p>\n<blockquote><p>&#8220;For instance, perhaps having multiple, tuned smaller models on-board devices with hierarchical inferencing algorithms will be sufficient for edge use cases.<\/p>\n<p>&#8220;AI algorithms and corresponding models will continue to evolve and, with the focus in our industry on sustainability, these models will quickly evolve to take less resources, becoming more appropriate for edge systems.&#8221;<\/p><\/blockquote>\n<h2><span id=\"an_ai_built_for_your_edge\">An AI Built for Your Edge<\/span><\/h2>\n<p>The 2023 Edge Advantage Report \u2014 which surveyed 600 enterprises across multiple industries \u2014 found that approximately <a href=\"https:\/\/services.global.ntt\/en-us\/insights\/2023-edge-advantage-report\" target=\"_blank\">70% of organizations<\/a> use edge solutions to solve business challenges. Still, nearly <strong>40% worry that their current infrastructure will not support advanced solutions<\/strong>.<\/p>\n<p>Bloudoff from NTT Data said that the company is well aware of the market\u00b4s concern and focuses on smaller, more efficient language models. These are easier to deploy and can run in real-time without demanding advanced edge hardware updates.<\/p>\n<p>Smaller AI models represent enormous savings in edge hardware costs for industries and businesses across the world. By going tiny, AI on the edge can maximize the edge computing power already in play through optimization.<\/p>\n<p>The company is also moving forward by implementing dozens of proofs of concepts with customers across manufacturing, automotive, healthcare, power generation, logistics, and other industries.<\/p>\n<h2><span id=\"the_bottom_line\">The Bottom Line<\/span><\/h2>\n<p>Supercomputers, quantum computers, and state-of-the-art AI racks hosted in massive data centers, are undoubtedly the tip of the spear of modern innovation. However, the real world works at the edge level.<\/p>\n<p>From the <a href=\"https:\/\/www.techopedia.com\/best-new-phones\">smartphone in your pocket<\/a> to the <a href=\"https:\/\/www.techopedia.com\/definition\/32099\/automation\">automation<\/a> of machines in industrial environments, healthcare, and agriculture, modern edge networks connect us all.<\/p>\n<p>As bigger, faster, harder, and stronger AI models roll out, NTT Data and IBM invest in small and tiny models. They believe it is the solution to the future of giant AIs in our edge world.<\/p>\n<div class=\"reference-content\">\n<div class=\"reference-heading reference-content-collapsible-heading\">\n<h2><span id=\"references\">References<\/span><\/h2>\n<\/div>\n<div class=\"reference-content-body\">\n<ol>\n<li><a href=\"https:\/\/www.redhat.com\/rhdc\/managed-files\/cl-451-research-on-edge-computing-analyst-material-1323765-202408-en.pdf\" target=\"_blank\">Industry-specific needs call for differentiated edge deployments<\/a> (Redhat)<\/li>\n<li><a href=\"https:\/\/www.idc.com\/getdoc.jsp?containerId=prUS51960324\" target=\"_blank\">New IDC Spending Guide Forecasts Edge Computing Investments Will Reach $232 Billion in 2024<\/a> (Idc)<\/li>\n<li><a href=\"https:\/\/www.linkedin.com\/in\/bloudoff\/\" target=\"_blank\">Paul Bloudoff &#8211; NTT Data Ltd. | LinkedIn<\/a> (Linkedin)<\/li>\n<li><a href=\"https:\/\/www.nttdata.com\/global\/en\/\" target=\"_blank\">Home | NTT Data Group<\/a> (Nttdata)<\/li>\n<li><a href=\"https:\/\/iot-analytics.com\/predictive-maintenance-market\/\" target=\"_blank\">Predictive maintenance market: 5 highlights for 2024 and beyond<\/a> (Iot-analytics)<\/li>\n<li><a href=\"https:\/\/www.sciencedirect.com\/science\/article\/abs\/pii\/S2666998624002473\" target=\"_blank\">Perspective. Shrinking the giants: Paving the way for TinyAI<\/a> (Sciencedirect)<\/li>\n<li><a href=\"https:\/\/www.linkedin.com\/in\/nicholascmfuller\/\" target=\"_blank\">Nicholas (Nick) Fuller &#8211; IBM | LinkedIn<\/a> (Linkedin)<\/li>\n<li><a href=\"https:\/\/research.ibm.com\/\" target=\"_blank\">A lab for the future of computing<\/a> (Research.ibm)<\/li>\n<li><a href=\"https:\/\/newsroom.ibm.com\/cait-crawford\" target=\"_blank\">IBM Newsroom &#8211; 2020 IBM Fellows<\/a> (Newsroom.ibm)<\/li>\n<li><a href=\"https:\/\/services.global.ntt\/en-us\/insights\/2023-edge-advantage-report\" target=\"_blank\">2023 Edge Advantage Report | NTT DATA<\/a> (Services.global)<\/li>\n<\/ol>\n<\/div>\n<\/div>\n","protected":false},"excerpt":{"rendered":"<p>One trillion plus AI parameter models are already banging hard at our front door. These new artificial intelligence models, with unprecedented computing power, will become the norm in the coming months and years ahead. While the technological advancements of new generative AI models are promising and expected to benefit most sectors and industries, the world [&hellip;]<\/p>\n","protected":false},"author":286688,"featured_media":307567,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"_lmt_disableupdate":"no","_lmt_disable":"","om_disable_all_campaigns":false,"footnotes":""},"categories":[606],"tags":[],"category_partsoff":[],"class_list":["post-307513","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-edge-computing"],"acf":[],"yoast_head":"<!-- This site is optimized with the Yoast SEO Premium plugin v24.2 (Yoast SEO v24.5) - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>IBM &amp; NTT Data Explain How AI Works on Edge Computing<\/title>\n<meta name=\"description\" content=\"Discover how NTT and IBM approach the problem of powering AI models at the edge computing level \u2014 to solve the \u2018shrinking giant\u2019 issue once and for all.\" \/>\n<meta name=\"robots\" content=\"noindex, follow\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"IBM &amp; NTT Data Explain How AI Works on Edge Computing\" \/>\n<meta property=\"og:description\" content=\"Discover how NTT and IBM approach the problem of powering AI models at the edge computing level \u2014 to solve the \u2018shrinking giant\u2019 issue once and for all.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.techopedia.com\/ibm-ntt-explain-how-ai-works-on-edge-computing\" \/>\n<meta property=\"og:site_name\" content=\"Techopedia\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/techopedia\/\" \/>\n<meta property=\"article:published_time\" content=\"2024-09-03T14:47:58+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-09-12T09:52:31+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.techopedia.com\/wp-content\/uploads\/2024\/09\/IBM-NTT-Explain-How-AI-Works-on-Edge-Computing.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1200\" \/>\n\t<meta property=\"og:image:height\" content=\"686\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"Ray Fernandez\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@techopedia\" \/>\n<meta name=\"twitter:site\" content=\"@techopedia\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Ray Fernandez\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"5 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/www.techopedia.com\/ibm-ntt-explain-how-ai-works-on-edge-computing#article\",\"isPartOf\":{\"@id\":\"https:\/\/www.techopedia.com\/ibm-ntt-explain-how-ai-works-on-edge-computing\"},\"author\":{\"name\":\"Ray Fernandez\",\"@id\":\"https:\/\/www.techopedia.com\/#\/schema\/person\/687890072e5e44867899acd7d6176e6c\"},\"headline\":\"IBM &#038; NTT Data Explain How AI Works on Edge Computing\",\"datePublished\":\"2024-09-03T14:47:58+00:00\",\"dateModified\":\"2024-09-12T09:52:31+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/www.techopedia.com\/ibm-ntt-explain-how-ai-works-on-edge-computing\"},\"wordCount\":1270,\"commentCount\":0,\"publisher\":{\"@id\":\"https:\/\/www.techopedia.com\/#organization\"},\"image\":{\"@id\":\"https:\/\/www.techopedia.com\/ibm-ntt-explain-how-ai-works-on-edge-computing#primaryimage\"},\"thumbnailUrl\":\"https:\/\/www.techopedia.com\/wp-content\/uploads\/2024\/09\/IBM-NTT-Explain-How-AI-Works-on-Edge-Computing.jpg\",\"articleSection\":\"\",\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\/\/www.techopedia.com\/ibm-ntt-explain-how-ai-works-on-edge-computing#respond\"]}],\"copyrightYear\":\"2024\",\"copyrightHolder\":{\"@id\":\"https:\/\/www.techopedia.com\/#organization\"}},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.techopedia.com\/ibm-ntt-explain-how-ai-works-on-edge-computing\",\"url\":\"https:\/\/www.techopedia.com\/ibm-ntt-explain-how-ai-works-on-edge-computing\",\"name\":\"IBM & NTT Data Explain How AI Works on Edge Computing\",\"isPartOf\":{\"@id\":\"https:\/\/www.techopedia.com\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/www.techopedia.com\/ibm-ntt-explain-how-ai-works-on-edge-computing#primaryimage\"},\"image\":{\"@id\":\"https:\/\/www.techopedia.com\/ibm-ntt-explain-how-ai-works-on-edge-computing#primaryimage\"},\"thumbnailUrl\":\"https:\/\/www.techopedia.com\/wp-content\/uploads\/2024\/09\/IBM-NTT-Explain-How-AI-Works-on-Edge-Computing.jpg\",\"datePublished\":\"2024-09-03T14:47:58+00:00\",\"dateModified\":\"2024-09-12T09:52:31+00:00\",\"description\":\"Discover how NTT and IBM approach the problem of powering AI models at the edge computing level \u2014 to solve the \u2018shrinking giant\u2019 issue once and for all.\",\"breadcrumb\":{\"@id\":\"https:\/\/www.techopedia.com\/ibm-ntt-explain-how-ai-works-on-edge-computing#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.techopedia.com\/ibm-ntt-explain-how-ai-works-on-edge-computing\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.techopedia.com\/ibm-ntt-explain-how-ai-works-on-edge-computing#primaryimage\",\"url\":\"https:\/\/www.techopedia.com\/wp-content\/uploads\/2024\/09\/IBM-NTT-Explain-How-AI-Works-on-Edge-Computing.jpg\",\"contentUrl\":\"https:\/\/www.techopedia.com\/wp-content\/uploads\/2024\/09\/IBM-NTT-Explain-How-AI-Works-on-Edge-Computing.jpg\",\"width\":1200,\"height\":686,\"caption\":\"IBM & NTT Explain How AI Works on Edge Computing\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.techopedia.com\/ibm-ntt-explain-how-ai-works-on-edge-computing#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/www.techopedia.com\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Networking\",\"item\":\"https:\/\/www.techopedia.com\/network\"},{\"@type\":\"ListItem\",\"position\":3,\"name\":\"Edge Computing\",\"item\":\"https:\/\/www.techopedia.com\/topic\/330\/edge-computing\"},{\"@type\":\"ListItem\",\"position\":4,\"name\":\"IBM &#038; NTT Data Explain How AI Works on Edge Computing\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.techopedia.com\/#website\",\"url\":\"https:\/\/www.techopedia.com\/\",\"name\":\"Techopedia\",\"description\":\"\",\"publisher\":{\"@id\":\"https:\/\/www.techopedia.com\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.techopedia.com\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/www.techopedia.com\/#organization\",\"name\":\"Techopedia\",\"url\":\"https:\/\/www.techopedia.com\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.techopedia.com\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/www.techopedia.com\/wp-content\/uploads\/2025\/02\/techopedia-light-logo.svg\",\"contentUrl\":\"https:\/\/www.techopedia.com\/wp-content\/uploads\/2025\/02\/techopedia-light-logo.svg\",\"caption\":\"Techopedia\"},\"image\":{\"@id\":\"https:\/\/www.techopedia.com\/#\/schema\/logo\/image\/\"},\"sameAs\":[\"https:\/\/www.facebook.com\/techopedia\/\",\"https:\/\/x.com\/techopedia\",\"https:\/\/www.linkedin.com\/company\/techopedia\/\",\"https:\/\/www.youtube.com\/c\/Techopedia\"],\"publishingPrinciples\":\"https:\/\/www.techopedia.com\/about\/editorial-policy\",\"ownershipFundingInfo\":\"https:\/\/www.techopedia.com\/about\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.techopedia.com\/#\/schema\/person\/687890072e5e44867899acd7d6176e6c\",\"name\":\"Ray Fernandez\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.techopedia.com\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/www.techopedia.com\/wp-content\/uploads\/2023\/10\/avatar_user_286688_1698354675-300x300.jpg\",\"contentUrl\":\"https:\/\/www.techopedia.com\/wp-content\/uploads\/2023\/10\/avatar_user_286688_1698354675-300x300.jpg\",\"caption\":\"Ray Fernandez\"},\"description\":\"Ray is an independent journalist with 15 years of experience, focusing on the intersection of technology with various aspects of life and society. He joined Techopedia in 2023 after publishing in numerous media, including Microsoft, TechRepublic, Moonlock, Hackermoon, VentureBeat, Entrepreneur, and ServerWatch. He holds a degree in Journalism from Oxford Distance Learning and two specializations from FUNIBER in Environmental Science and Oceanography. When Ray is not working, you can find him making music, playing sports, and traveling with his wife and three kids.\",\"sameAs\":[\"https:\/\/www.linkedin.com\/in\/ray-fernandez\/\"],\"knowsAbout\":[\"Senior Technology Journalist\"],\"url\":\"https:\/\/www.techopedia.com\/contributors\/rayfernandez\"}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"IBM & NTT Data Explain How AI Works on Edge Computing","description":"Discover how NTT and IBM approach the problem of powering AI models at the edge computing level \u2014 to solve the \u2018shrinking giant\u2019 issue once and for all.","robots":{"index":"noindex","follow":"follow"},"og_locale":"en_US","og_type":"article","og_title":"IBM & NTT Data Explain How AI Works on Edge Computing","og_description":"Discover how NTT and IBM approach the problem of powering AI models at the edge computing level \u2014 to solve the \u2018shrinking giant\u2019 issue once and for all.","og_url":"https:\/\/www.techopedia.com\/ibm-ntt-explain-how-ai-works-on-edge-computing","og_site_name":"Techopedia","article_publisher":"https:\/\/www.facebook.com\/techopedia\/","article_published_time":"2024-09-03T14:47:58+00:00","article_modified_time":"2024-09-12T09:52:31+00:00","og_image":[{"width":1200,"height":686,"url":"https:\/\/www.techopedia.com\/wp-content\/uploads\/2024\/09\/IBM-NTT-Explain-How-AI-Works-on-Edge-Computing.jpg","type":"image\/jpeg"}],"author":"Ray Fernandez","twitter_card":"summary_large_image","twitter_creator":"@techopedia","twitter_site":"@techopedia","twitter_misc":{"Written by":"Ray Fernandez","Est. reading time":"5 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/www.techopedia.com\/ibm-ntt-explain-how-ai-works-on-edge-computing#article","isPartOf":{"@id":"https:\/\/www.techopedia.com\/ibm-ntt-explain-how-ai-works-on-edge-computing"},"author":{"name":"Ray Fernandez","@id":"https:\/\/www.techopedia.com\/#\/schema\/person\/687890072e5e44867899acd7d6176e6c"},"headline":"IBM &#038; NTT Data Explain How AI Works on Edge Computing","datePublished":"2024-09-03T14:47:58+00:00","dateModified":"2024-09-12T09:52:31+00:00","mainEntityOfPage":{"@id":"https:\/\/www.techopedia.com\/ibm-ntt-explain-how-ai-works-on-edge-computing"},"wordCount":1270,"commentCount":0,"publisher":{"@id":"https:\/\/www.techopedia.com\/#organization"},"image":{"@id":"https:\/\/www.techopedia.com\/ibm-ntt-explain-how-ai-works-on-edge-computing#primaryimage"},"thumbnailUrl":"https:\/\/www.techopedia.com\/wp-content\/uploads\/2024\/09\/IBM-NTT-Explain-How-AI-Works-on-Edge-Computing.jpg","articleSection":"","inLanguage":"en-US","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/www.techopedia.com\/ibm-ntt-explain-how-ai-works-on-edge-computing#respond"]}],"copyrightYear":"2024","copyrightHolder":{"@id":"https:\/\/www.techopedia.com\/#organization"}},{"@type":"WebPage","@id":"https:\/\/www.techopedia.com\/ibm-ntt-explain-how-ai-works-on-edge-computing","url":"https:\/\/www.techopedia.com\/ibm-ntt-explain-how-ai-works-on-edge-computing","name":"IBM & NTT Data Explain How AI Works on Edge Computing","isPartOf":{"@id":"https:\/\/www.techopedia.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.techopedia.com\/ibm-ntt-explain-how-ai-works-on-edge-computing#primaryimage"},"image":{"@id":"https:\/\/www.techopedia.com\/ibm-ntt-explain-how-ai-works-on-edge-computing#primaryimage"},"thumbnailUrl":"https:\/\/www.techopedia.com\/wp-content\/uploads\/2024\/09\/IBM-NTT-Explain-How-AI-Works-on-Edge-Computing.jpg","datePublished":"2024-09-03T14:47:58+00:00","dateModified":"2024-09-12T09:52:31+00:00","description":"Discover how NTT and IBM approach the problem of powering AI models at the edge computing level \u2014 to solve the \u2018shrinking giant\u2019 issue once and for all.","breadcrumb":{"@id":"https:\/\/www.techopedia.com\/ibm-ntt-explain-how-ai-works-on-edge-computing#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.techopedia.com\/ibm-ntt-explain-how-ai-works-on-edge-computing"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.techopedia.com\/ibm-ntt-explain-how-ai-works-on-edge-computing#primaryimage","url":"https:\/\/www.techopedia.com\/wp-content\/uploads\/2024\/09\/IBM-NTT-Explain-How-AI-Works-on-Edge-Computing.jpg","contentUrl":"https:\/\/www.techopedia.com\/wp-content\/uploads\/2024\/09\/IBM-NTT-Explain-How-AI-Works-on-Edge-Computing.jpg","width":1200,"height":686,"caption":"IBM & NTT Explain How AI Works on Edge Computing"},{"@type":"BreadcrumbList","@id":"https:\/\/www.techopedia.com\/ibm-ntt-explain-how-ai-works-on-edge-computing#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.techopedia.com\/"},{"@type":"ListItem","position":2,"name":"Networking","item":"https:\/\/www.techopedia.com\/network"},{"@type":"ListItem","position":3,"name":"Edge Computing","item":"https:\/\/www.techopedia.com\/topic\/330\/edge-computing"},{"@type":"ListItem","position":4,"name":"IBM &#038; NTT Data Explain How AI Works on Edge Computing"}]},{"@type":"WebSite","@id":"https:\/\/www.techopedia.com\/#website","url":"https:\/\/www.techopedia.com\/","name":"Techopedia","description":"","publisher":{"@id":"https:\/\/www.techopedia.com\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.techopedia.com\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/www.techopedia.com\/#organization","name":"Techopedia","url":"https:\/\/www.techopedia.com\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.techopedia.com\/#\/schema\/logo\/image\/","url":"https:\/\/www.techopedia.com\/wp-content\/uploads\/2025\/02\/techopedia-light-logo.svg","contentUrl":"https:\/\/www.techopedia.com\/wp-content\/uploads\/2025\/02\/techopedia-light-logo.svg","caption":"Techopedia"},"image":{"@id":"https:\/\/www.techopedia.com\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.facebook.com\/techopedia\/","https:\/\/x.com\/techopedia","https:\/\/www.linkedin.com\/company\/techopedia\/","https:\/\/www.youtube.com\/c\/Techopedia"],"publishingPrinciples":"https:\/\/www.techopedia.com\/about\/editorial-policy","ownershipFundingInfo":"https:\/\/www.techopedia.com\/about"},{"@type":"Person","@id":"https:\/\/www.techopedia.com\/#\/schema\/person\/687890072e5e44867899acd7d6176e6c","name":"Ray Fernandez","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.techopedia.com\/#\/schema\/person\/image\/","url":"https:\/\/www.techopedia.com\/wp-content\/uploads\/2023\/10\/avatar_user_286688_1698354675-300x300.jpg","contentUrl":"https:\/\/www.techopedia.com\/wp-content\/uploads\/2023\/10\/avatar_user_286688_1698354675-300x300.jpg","caption":"Ray Fernandez"},"description":"Ray is an independent journalist with 15 years of experience, focusing on the intersection of technology with various aspects of life and society. He joined Techopedia in 2023 after publishing in numerous media, including Microsoft, TechRepublic, Moonlock, Hackermoon, VentureBeat, Entrepreneur, and ServerWatch. He holds a degree in Journalism from Oxford Distance Learning and two specializations from FUNIBER in Environmental Science and Oceanography. When Ray is not working, you can find him making music, playing sports, and traveling with his wife and three kids.","sameAs":["https:\/\/www.linkedin.com\/in\/ray-fernandez\/"],"knowsAbout":["Senior Technology Journalist"],"url":"https:\/\/www.techopedia.com\/contributors\/rayfernandez"}]}},"modified_by":"Eddie Wrenn","_links":{"self":[{"href":"https:\/\/www.techopedia.com\/wp-json\/wp\/v2\/posts\/307513","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.techopedia.com\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.techopedia.com\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.techopedia.com\/wp-json\/wp\/v2\/users\/286688"}],"replies":[{"embeddable":true,"href":"https:\/\/www.techopedia.com\/wp-json\/wp\/v2\/comments?post=307513"}],"version-history":[{"count":5,"href":"https:\/\/www.techopedia.com\/wp-json\/wp\/v2\/posts\/307513\/revisions"}],"predecessor-version":[{"id":313022,"href":"https:\/\/www.techopedia.com\/wp-json\/wp\/v2\/posts\/307513\/revisions\/313022"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.techopedia.com\/wp-json\/wp\/v2\/media\/307567"}],"wp:attachment":[{"href":"https:\/\/www.techopedia.com\/wp-json\/wp\/v2\/media?parent=307513"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.techopedia.com\/wp-json\/wp\/v2\/categories?post=307513"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.techopedia.com\/wp-json\/wp\/v2\/tags?post=307513"},{"taxonomy":"category_partsoff","embeddable":true,"href":"https:\/\/www.techopedia.com\/wp-json\/wp\/v2\/category_partsoff?post=307513"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}