{"id":13065,"date":"2021-01-11T09:00:00","date_gmt":"2021-01-11T08:00:00","guid":{"rendered":"https:\/\/www.codemotion.com\/magazine\/?p=13065"},"modified":"2023-06-23T15:18:49","modified_gmt":"2023-06-23T13:18:49","slug":"machine-learning-network-edge","status":"publish","type":"post","link":"https:\/\/www.codemotion.com\/magazine\/ai-ml\/machine-learning\/machine-learning-network-edge\/","title":{"rendered":"The Rise of Machine Learning at the Network Edge"},"content":{"rendered":"\r\n<p>Over the past few months, I have shown you why <strong style=\"user-select: auto;\"><span id=\"urn:enhancement-916b9a5e\" class=\"textannotation disambiguated wl-thing\">machine learning<\/span> at the network edge<\/strong> is so essential. In this final article, we look back at why machine learning is needed and look at some of the real-world cases where it has already been transformative.<\/p>\r\n\r\n\r\n\t\t\t\t<div class=\"wp-block-uagb-table-of-contents uagb-toc__align-left uagb-toc__columns-1  uagb-block-e061a166      \"\n\t\t\t\t\tdata-scroll= \"1\"\n\t\t\t\t\tdata-offset= \"30\"\n\t\t\t\t\tstyle=\"\"\n\t\t\t\t>\n\t\t\t\t<div class=\"uagb-toc__wrap\">\n\t\t\t\t\t\t<div class=\"uagb-toc__title\">\n\t\t\t\t\t\t\tTable Of Contents\t\t\t\t\t\t<\/div>\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<div class=\"uagb-toc__list-wrap \">\n\t\t\t\t\t\t<ol class=\"uagb-toc__list\"><li class=\"uagb-toc__list\"><a href=\"#why-is-machine-learning-needed-at-the-network-edge\" class=\"uagb-toc-link__trigger\">Why is Machine Learning needed at the network edge?<\/a><ul class=\"uagb-toc__list\"><li class=\"uagb-toc__list\"><a href=\"#real-time-performance\" class=\"uagb-toc-link__trigger\">Real-time performance<\/a><li class=\"uagb-toc__list\"><li class=\"uagb-toc__list\"><a href=\"#security-and-privacy\" class=\"uagb-toc-link__trigger\">Security and privacy<\/a><li class=\"uagb-toc__list\"><li class=\"uagb-toc__list\"><a href=\"#network-connectivity\" class=\"uagb-toc-link__trigger\">Network connectivity<\/a><\/li><\/ul><\/li><li class=\"uagb-toc__list\"><a href=\"#how-do-we-enable-edge-machine-learning\" class=\"uagb-toc-link__trigger\">How do we enable edge Machine Learning?<\/a><ul class=\"uagb-toc__list\"><li class=\"uagb-toc__list\"><a href=\"#what-hardware-is-available\" class=\"uagb-toc-link__trigger\">What hardware is available?<\/a><li class=\"uagb-toc__list\"><li class=\"uagb-toc__list\"><a href=\"#how-about-software-support\" class=\"uagb-toc-link__trigger\">How about software support?<\/a><\/li><\/ul><\/li><\/ul><\/li><li class=\"uagb-toc__list\"><a href=\"#real-world-examples-of-edge-ml\" class=\"uagb-toc-link__trigger\">Real-world examples of edge ML<\/a><ul class=\"uagb-toc__list\"><li class=\"uagb-toc__list\"><a href=\"#real-time-facial-recognition\" class=\"uagb-toc-link__trigger\">Real-time facial recognition<\/a><li class=\"uagb-toc__list\"><li class=\"uagb-toc__list\"><a href=\"#smart-headphones-and-speakers\" class=\"uagb-toc-link__trigger\">Smart headphones and speakers<\/a><li class=\"uagb-toc__list\"><li class=\"uagb-toc__list\"><a href=\"#self-driving-cars\" class=\"uagb-toc-link__trigger\">Self-driving cars<\/a><\/li><\/ul><\/li><\/ul><\/li><\/ul><\/li><li class=\"uagb-toc__list\"><a href=\"#whats-next-for-edge-ml\" class=\"uagb-toc-link__trigger\">What\u2019s next for edge ML?<\/a><li class=\"uagb-toc__list\"><a href=\"#future-edge-machine-learning-applications\" class=\"uagb-toc-link__trigger\">Future edge Machine Learning applications<\/a><ul class=\"uagb-toc__list\"><li class=\"uagb-toc__list\"><a href=\"#true-intelligent-sensors\" class=\"uagb-toc-link__trigger\">True intelligent sensors<\/a><li class=\"uagb-toc__list\"><li class=\"uagb-toc__list\"><a href=\"#autonomous-digital-assistants\" class=\"uagb-toc-link__trigger\">Autonomous digital assistants<\/a><li class=\"uagb-toc__list\"><li class=\"uagb-toc__list\"><a href=\"#intelligent-security-systems\" class=\"uagb-toc-link__trigger\">Intelligent security systems<\/a><\/li><\/ul><\/li><\/ul><\/li><\/ul><\/li><\/ul><\/li><li class=\"uagb-toc__list\"><a href=\"#conclusions\" class=\"uagb-toc-link__trigger\">Conclusions<\/a><\/ul><\/ul><\/ul><\/ul><\/ol>\t\t\t\t\t<\/div>\n\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\r\n\r\n\r\n<h2 class=\"wp-block-heading\" id=\"h-why-is-machine-learning-needed-at-the-network-edge\">Why is Machine Learning needed at the network edge?<\/h2>\r\n\r\n\r\n\r\n<p>Machine learning is the core technology for smart homes, autonomous vehicles, and intelligent <span id=\"urn:enhancement-a5e433c6\" class=\"textannotation disambiguated wl-thing\">automation<\/span>. All these applications take place at (or beyond) the network edge. However, most <span id=\"urn:enhancement-64a3435\" class=\"textannotation disambiguated wl-creative-work\">ML<\/span> models need the sort of <span id=\"urn:enhancement-c74c1c66\" class=\"textannotation disambiguated wl-thing\">computing power<\/span> you can only get in the <span id=\"urn:enhancement-21aa87c\" class=\"textannotation disambiguated wl-thing\">cloud<\/span>.\u00a0<\/p>\r\n\r\n\r\n\r\n<p>This is especially true when it comes to training new models. But what happens when you can\u2019t run your model in a data centre? Then you need to rely on running ML models on <span id=\"urn:enhancement-326ae3fd\" class=\"textannotation disambiguated wl-thing\">edge devices<\/span>.<\/p>\r\n\r\n\r\n\r\n<p>There are several reasons why you can\u2019t run a model in the cloud. The three that matter the most are explained here.<\/p>\r\n\r\n\r\n\r\n<h3 class=\"wp-block-heading\" id=\"h-real-time-performance\">Real-time performance<\/h3>\r\n\r\n\r\n\r\n<p>Many edge ML applications rely on working in <span id=\"urn:enhancement-66b22cfd\" class=\"textannotation disambiguated wl-thing\">real-time<\/span>. That is, they need the ML model to give a result almost instantaneously. Two key examples of this are:<\/p>\r\n\r\n\r\n\r\n<ul class=\"wp-block-list\">\r\n<li><strong><span id=\"urn:enhancement-faf58a3c\" class=\"textannotation disambiguated wl-thing\">Self-driving cars<\/span><\/strong>. Clearly, self-driving cars need to react as fast as possible to the world around them. They will rely on a range of different <span id=\"urn:enhancement-303894ff\" class=\"textannotation disambiguated wl-thing\">sensors<\/span> to gather data about current driving conditions. These include cameras, <span id=\"urn:enhancement-8f3c6c18\" class=\"textannotation disambiguated wl-thing\">LiDAR<\/span>, radar, and time-of-flight cameras. These sensors produce a range of inputs that need to be analysed and combined in real-time.<\/li>\r\n<li><strong>Safety systems in factories<\/strong>. Automation has allowed factories to become far safer in recent years. However, there are still potential dangers, not least because production lines are often monitored by just one person. Increasingly, factories rely on sensors to understand what is happening in real-time. These perform various tasks, such as detecting unexpected objects and identifying broken tools.<\/li>\r\n<\/ul>\r\n\r\n\r\n\r\n<h3 class=\"wp-block-heading\" id=\"h-security-and-privacy\">Security and privacy<\/h3>\r\n\r\n\r\n\r\n<p>Some applications of ML handle sensitive data. For instance, medical data related to <span id=\"urn:enhancement-50bf1249\" class=\"textannotation disambiguated wl-thing\">AI<\/span> for patient diagnosis. This data is viewed as especially sensitive in many countries. For instance, in the EU it receives extra protections under <span id=\"urn:enhancement-4e329a2\" class=\"textannotation disambiguated wl-thing\">GDPR<\/span>. Sending this data across the network to a remote data centre may be undesirable.<\/p>\r\n\r\n\r\n\r\n<p>Likewise, some security applications may require local processing. For instance, smart door entry systems at government sensitive sites. Here, it is probably best not to send photos of every visitor across the network to verify them against a central database.\u00a0<\/p>\r\n\r\n\r\n\r\n<h3 class=\"wp-block-heading\" id=\"h-network-connectivity\">Network connectivity<\/h3>\r\n\r\n\r\n\r\n<p>There are many locations where edge ML is the only option due to the lack of network connectivity. This can be due to two reasons. Either, there simply is no network due to the remote location. Or, local network policies forbid connections to the Internet.\u00a0<\/p>\r\n\r\n\r\n\r\n<p>The former happens regularly in heavy industry, mining, and agriculture. Take modern farming for instance. Nowadays, agriculture is driven by big data and edge ML is used to boost yield and cut the environmental impact.\u00a0<\/p>\r\n\r\n\r\n\r\n<p>Combine harvesters monitor yield in fields to the nearest square metre. Fertiliser sprayers can adapt the amount of fertiliser they deliver based on monitoring the crop using cameras.\u00a0<\/p>\r\n\r\n\r\n\r\n<h2 class=\"wp-block-heading\" id=\"h-how-do-we-enable-edge-machine-learning\">How do we enable edge Machine Learning?<\/h2>\r\n\r\n\r\n\r\n<p>Machine learning at the edge has become feasible thanks to two developments. Firstly, low-cost MCUs now have sufficient processing power to power machine learning models. Secondly, a number of <span id=\"urn:enhancement-cf994fe2\" class=\"textannotation disambiguated wl-thing\">frameworks<\/span> have been developed specifically for edge ML.<\/p>\r\n\r\n\r\n\r\n<h3 class=\"wp-block-heading\" id=\"h-what-hardware-is-available\">What hardware is available?<\/h3>\r\n\r\n\r\n\r\n<p>We already saw the sort of affordable <span id=\"urn:enhancement-9a56d38f\" class=\"textannotation disambiguated wl-thing\">hardware<\/span> that can power edge ML. Mostly, this will be some form of <span id=\"urn:enhancement-73e346aa\" class=\"textannotation disambiguated wl-thing\">MCU<\/span> with an embedded <span id=\"urn:enhancement-77c1ae2e\" class=\"textannotation disambiguated wl-thing\">ARM<\/span> Cortex core. The following table shows some of the more popular options.<\/p>\r\n\r\n\r\n\r\n<figure class=\"wp-block-table\">\r\n<table>\r\n<tbody>\r\n<tr>\r\n<td><strong>Board<\/strong><\/td>\r\n<td><strong>Processor<\/strong><\/td>\r\n<td><strong>Core<\/strong><\/td>\r\n<td><strong>Speed<\/strong><\/td>\r\n<\/tr>\r\n<tr>\r\n<td>NXP i.MX RT1050 EVK\u00a0<\/td>\r\n<td>MIMXRT1052DVL6A<\/td>\r\n<td>Cortex-M7<\/td>\r\n<td>Up to 600MHz<\/td>\r\n<\/tr>\r\n<tr>\r\n<td>Microchip SAM E54 Xplained Pro<\/td>\r\n<td>ATSAME54P20A<\/td>\r\n<td>Cortex-M4<\/td>\r\n<td>Up to 120MHz<\/td>\r\n<\/tr>\r\n<tr>\r\n<td>Infineon XMC4700 Relax Kit\u00a0<\/td>\r\n<td>XMC4700-F144<\/td>\r\n<td>Cortex-M4<\/td>\r\n<td>144MHz<\/td>\r\n<\/tr>\r\n<tr>\r\n<td>SiLabs SLSTK3701A starter kit<\/td>\r\n<td>EFM32 Giant Gecko 11<\/td>\r\n<td>Cortex-M4<\/td>\r\n<td>72MHz<\/td>\r\n<\/tr>\r\n<tr>\r\n<td><span id=\"urn:enhancement-1c0fa8ba\" class=\"textannotation disambiguated wl-creative-work\">Arduino<\/span> Nano 33 BLE Sense<\/td>\r\n<td>nRF52840<\/td>\r\n<td>Cortex-M4<\/td>\r\n<td>64MHz<\/td>\r\n<\/tr>\r\n<\/tbody>\r\n<\/table>\r\n<\/figure>\r\n\r\n\r\n\r\n<p>In future, we will see more specialised system-on-a-chip or <span id=\"urn:enhancement-1cd557f4\" class=\"textannotation disambiguated wl-thing\">SoC<\/span> solutions. SoCs deliver the fast processing, graphics, sensing, network connectivity, and other features we expect in a modern <span id=\"urn:enhancement-2778d5ee\" class=\"textannotation disambiguated wl-thing\">smartphone<\/span>. The latest, such as <span id=\"urn:enhancement-c063453f\" class=\"textannotation disambiguated wl-organization\">Apple<\/span>\u2019s A13, now include specialised hardware specifically for running neural network machine learning models.<\/p>\r\n\r\n\r\n\r\n<h3 class=\"wp-block-heading\" id=\"h-how-about-software-support\">How about software support?<\/h3>\r\n\r\n\r\n\r\n<p>Most machine learning models are typically created using a framework or set of libraries. Two of the most popular are:<\/p>\r\n\r\n\r\n\r\n<ul class=\"wp-block-list\">\r\n<li><a href=\"https:\/\/www.tensorflow.org\/\">TensorFlow<\/a>. This was developed by <span id=\"urn:enhancement-966cea0f\" class=\"textannotation disambiguated wl-organization\">Google<\/span> but released under <span id=\"urn:enhancement-69e4cb89\" class=\"textannotation disambiguated wl-thing\">opensource<\/span> license. This framework (officially a platform) makes it easy to develop ML models anywhere.<\/li>\r\n<li><a href=\"https:\/\/pytorch.org\/\">PyTorch<\/a>. This is <span id=\"urn:enhancement-ca94ecb2\" class=\"textannotation disambiguated wl-creative-work\">Facebook<\/span>\u2019s extension to the <a href=\"https:\/\/en.wikipedia.org\/wiki\/Torch_(machine_learning)\">Torch<\/a> ML library. <span id=\"urn:enhancement-6c85e32a\" class=\"textannotation disambiguated wl-thing\">PyTorch<\/span> simplifies the creation of ML models in <span id=\"urn:enhancement-a9b9678b\" class=\"textannotation disambiguated wl-creative-work\">Python<\/span>. It leverages <a href=\"https:\/\/numpy.org\/\">NumPy<\/a> to offer high performance and accuracy.<\/li>\r\n<\/ul>\r\n\r\n\r\n\r\n<p>Both of these frameworks offer versions that are optimised for running at the network edge. <a href=\"https:\/\/www.tensorflow.org\/lite\">TensorFlow Lite<\/a> allows you to export any TensorFlow model and run it on a variety of edge devices. <a href=\"https:\/\/pytorch.org\/mobile\">PyTorch Mobile<\/a> allows PyTorch models to be run on SoC-based systems.\u00a0<\/p>\r\n\r\n\r\n\r\n<p>In a <a style=\"user-select: auto;\" href=\"https:\/\/www.codemotion.com\/magazine\/dev-hub\/machine-learning-dev\/edge-machine-learning\/\">previous article<\/a>, I showed you how to convert a TensorFLow model to TensorFlow Lite. As I explained then, there are some limitations that mean you can\u2019t simply convert every existing model.<\/p>\r\n\r\n\r\n\r\n<p>However, each new release of TensorFlow Lite reduces these limitations further. Currently, the greatest limitation relates to data types. While tf.float32, tf.int8 and tf.uint8 are always supported, some operations don\u2019t support tf.float16 or tf.string.<\/p>\r\n\r\n\r\n\r\n<h2 class=\"wp-block-heading\" id=\"h-real-world-examples-of-edge-ml\">Real-world examples of edge ML<\/h2>\r\n\r\n\r\n\r\n<p>Over this series, I showed you several practical examples of edge ML, such as <a href=\"https:\/\/www.codemotion.com\/magazine\/dev-hub\/machine-learning-dev\/machine-learning-edge-example\/\">gesture recognition<\/a>, <a href=\"https:\/\/www.codemotion.com\/magazine\/dev-hub\/machine-learning-dev\/image-recognition-on-mcu\/\">computer vision<\/a>, and <a href=\"https:\/\/www.codemotion.com\/magazine\/dev-hub\/machine-learning-dev\/voice-control\/\">voice control<\/a>. All these examples relied on existing ML models and were relatively simple. But what about more realistic applications of edge ML?\u00a0<\/p>\r\n\r\n\r\n\r\n<h3 class=\"wp-block-heading\" id=\"h-real-time-facial-recognition\">Real-time facial recognition<\/h3>\r\n\r\n\r\n\r\n<p>Police forces and security services need to be able to spot trouble-makers at demonstrations or sporting events. For years, they have employed so-called <a href=\"https:\/\/en.wikipedia.org\/wiki\/Super_recogniser\">super-recognisers<\/a>\u2014people with an almost superhuman ability to recognise faces. These people look through thousands of police mugshots and learn to identify known hooligans or extremists.\u00a0<\/p>\r\n\r\n\r\n\r\n<p>Then, at the event, they scan the crowd looking for people they recognise. Unfortunately, this super-recogniser skill is rare. If you want to find out if you have this skill, you can check out the Greenwich University <a href=\"https:\/\/www.superrecognisers.com\/\">Super-Recogniser test<\/a>.\u00a0<\/p>\r\n\r\n\r\n\r\n<figure class=\"wp-block-image\"><img decoding=\"async\" src=\"https:\/\/lh4.googleusercontent.com\/P4EA9yvlg2RWxsEq6OxZP_4nGehvO6rOMhlWxOD99gH6W0LFHJ7tWrDk94tWMvkLEWO4iEkQMK2yFTnUwxXk9UkH9r7KWmGNI7CN2CzBPsCw4sj26STlczu4l7ePks1Ubh6J88co\" alt=\"The Greenwich University Super-Recogniser test\" \/>\r\n<figcaption><em>The Greenwich University Super-Recogniser test<\/em>.<\/figcaption>\r\n<\/figure>\r\n\r\n\r\n\r\n<p>Fortunately, facial recognition systems are increasingly able to perform as well as humans (albeit, with some teething issues relating to <span id=\"urn:enhancement-df7eaed6\" class=\"textannotation disambiguated wl-thing\">bias<\/span>). Usually, this involves uploading footage for analysis in the cloud. However, in a real-world situation, the police need to be able to recognise people in real-time.\u00a0<\/p>\r\n\r\n\r\n\r\n<p>Often, there will only be limited network connectivity too. Thus, they need to rely on edge-ML to achieve this. Currently, most of these solutions rely on <span id=\"urn:enhancement-3eb42ff8\" class=\"textannotation disambiguated wl-thing\">CPUs<\/span>, rather than MCUs. One example is Advantech\u2019s Video AI Facial Recognition Edge.<\/p>\r\n\r\n\r\n\r\n<h3 class=\"wp-block-heading\" id=\"h-smart-headphones-and-speakers\">Smart headphones and speakers<\/h3>\r\n\r\n\r\n\r\n<p>Modern headphones and Bluetooth speakers are no longer just a way to listen to music on the go. Nowadays, they routinely include smart features like noice cancellation and digital assistants. But how is that possible in a device that is sometimes small enough to fit inside your ear? The answer is by using highly-specialised SoCs.\u00a0<\/p>\r\n\r\n\r\n\r\n<p>One good example is NXP\u2019s <a style=\"user-select: auto;\" href=\"https:\/\/eu.mouser.com\/new\/nxp-semiconductors\/nxp-sln-alexa-iot\/\">MCU-based solutions for Alexa Voice<\/a>. These are specifically designed for integration into smart devices all over the home. These are based on the i.MX RT1060 high-performance MCU with an embedded Cortex-M7 ARM core. They come with integrated Bluetooth and WiFi for maximum connectivity.<\/p>\r\n\r\n\r\n\r\n<p>Currently, they are able to do always-on voice recognition, listening for and reacting to \u201cwake words\u201d. In future, these will likely become powerful enough to run complete voice control ML models.<\/p>\r\n\r\n\r\n\r\n<h3 class=\"wp-block-heading\" id=\"h-self-driving-cars\">Self-driving cars<\/h3>\r\n\r\n\r\n\r\n<p>I already mentioned that self-driving cars rely on edge-ML to allow them to operate safely. SAE International identifies 5 levels of automation for self-driving vehicles. These are show in the table below.<\/p>\r\n\r\n\r\n\r\n<figure class=\"wp-block-image\"><img decoding=\"async\" src=\"https:\/\/lh5.googleusercontent.com\/HNNpsiAqayALi8oCEMJ01x2vYwlIk5zSVNMknPQTvSU7kXypReA88_hDG-Lggmd31R9ED8NhnbTLYEcKR_FUO34bZ4lvxaIwOvsJWNhbcs1xyj6k9Qi-EbgSUz3vVCLYGCIpoz_p\" alt=\"SAE International 5 levels of driving automation\" \/>\r\n<figcaption><em>SAE International 5 levels of driving automation<\/em><\/figcaption>\r\n<\/figure>\r\n\r\n\r\n\r\n<p>Most modern cars achieve some level of automation. For instance, lane centering with adaptive cruise control is a common feature on many cars. This system will ensure the car remains between the lines on the highway and will prevent it getting too close to the vehicle in front. Systems like this rely heavily on embedded MCUs running simple edge ML models.<\/p>\r\n\r\n\r\n\r\n<p>As you move up to SAE level 4 or 5, you need to use far more complex models. At this level, you start to rely on highly specialised single-board computers, such as the <a href=\"https:\/\/www.nvidia.com\/en-us\/self-driving-cars\/drive-platform\/hardware\/\">NVIDIA DRIVE AGX Pegasus<\/a>.\u00a0<\/p>\r\n\r\n\r\n\r\n<p>This is described as an embedded supercomputing platform, and is capable of 320 trillion operations per second. For comparison, that is approximately the same as the latest generation of AMD Ryzen desktop CPU. However, the NVIDIA system is specifically optimised for machine learning with two embedded GPUs.<\/p>\r\n\r\n\r\n\r\n<figure class=\"wp-block-image\"><img decoding=\"async\" src=\"https:\/\/lh5.googleusercontent.com\/lM7JZPYyurZVAOQi0WWh-E6E-MYt1timLVPnrXccLAXZ7nkSWCjenSAtfk-qgs5Og2jlUpoXQdAFSOmR_DbSW17r5ECcFgR4FyW4RP4pkxn_BTSTgmoKY6X0AHALXcZJ0SSxpGEq\" alt=\"NVIDIA DRIVE AGX Pegasus uses 2 Turing GPUs and 2 Xavier SoCs\" \/>\r\n<figcaption><em>NVIDIA DRIVE AGX Pegasus uses 2 Turing GPUs and 2 Xavier SoCs<\/em><\/figcaption>\r\n<\/figure>\r\n\r\n\r\n\r\n<p>Before long, we will see systems that effectively integrate the GPU and processing cores into a single SoC.\u00a0<\/p>\r\n\r\n\r\n\r\n<h2 class=\"wp-block-heading\" id=\"h-what-s-next-for-edge-ml\">What\u2019s next for edge ML?<\/h2>\r\n\r\n\r\n\r\n<p>In many ways, we are still in the infancy of edge ML. But there is no doubt in my mind that it is going to grow and grow as a field. So, what applications might we see in the future? Last time, I looked at how the increasing performance of MCUs will allow new forms of ML at the edge. Specifically, I identified three areas:<\/p>\r\n\r\n\r\n\r\n<ul class=\"wp-block-list\">\r\n<li><strong>Unsupervised learning<\/strong>. This is where a computer builds its own model from data that has not been labelled or processed in advance. Often, it is used in combination with supervised learning through a process known as boosting.\u00a0<\/li>\r\n<\/ul>\r\n\r\n\r\n\r\n<ul class=\"wp-block-list\">\r\n<li><strong>Deep learning<\/strong>. Currently, this is the nearest computers can come to true human-like intelligence. Deep learning involves the use of enormous deep neural networks to tackle problems. Google <a href=\"https:\/\/deepmind.com\/\">DeepMind<\/a> is probably the world-leader here. It has demonstrated some remarkable feats, including <a href=\"https:\/\/deepmind.com\/blog\/article\/alphafold-a-solution-to-a-50-year-old-grand-challenge-in-biology\">solving the protein folding problem<\/a>.<\/li>\r\n<\/ul>\r\n\r\n\r\n\r\n<ul class=\"wp-block-list\">\r\n<li><strong>Continuous learning<\/strong>. Supervised learning models often become outdated as soon as they are created. For instance, stock predictions for fashion retailers don\u2019t just depend on the current weather and season. They also change rapidly as fashions come and go. <a href=\"https:\/\/www.codemotion.com\/magazine\/dev-hub\/backend-dev\/developers-continuous-learning-upskilling-cross-training\/\" target=\"_blank\" rel=\"noopener\">Continuous learning<\/a> solves this by constantly updating the model based on the latest data.<\/li>\r\n<\/ul>\r\n\r\n\r\n\r\n<h2 class=\"wp-block-heading\" id=\"h-future-edge-machine-learning-applications\">Future edge Machine Learning applications<\/h2>\r\n\r\n\r\n\r\n<p>The above advances will open up some important new applications for edge ML. Here are my three predictions for the near future.<\/p>\r\n\r\n\r\n\r\n<h3 class=\"wp-block-heading\" id=\"h-true-intelligent-sensors\">True intelligent sensors<\/h3>\r\n\r\n\r\n\r\n<p>The Internet of Things (IoT) has been much-hyped in recent years. But so far, it has failed to deliver its full potential. This is because it relies on simple sensors. These sensors are then connected together and feed their data to a central system for processing. This creates two drawbacks.\u00a0<\/p>\r\n\r\n\r\n\r\n<p>Firstly, the systems only work when three is really good connectivity. In fact, IoT is one of the key drivers behind the rollout of 5G technology. Secondly, this need for constant connectivity greatly increases the power drawn.\u00a0<\/p>\r\n\r\n\r\n\r\n<p>In the near future, we will see intelligent sensors that use an on-board MCU to do much of the processing. They will only need to connect to the central system if they identify a problem. Potentially, they may even be able to respond directly, for instance cutting power to a system that is failing.<\/p>\r\n\r\n\r\n\r\n<h3 class=\"wp-block-heading\" id=\"h-autonomous-digital-assistants\">Autonomous digital assistants<\/h3>\r\n\r\n\r\n\r\n<p>Digital assistants like Alexa, Siri, and Google Assistant are all round us. However, all these systems rely on being permanently connected to the cloud. This is needed because accurate speech recognition and voice control still need quite significant processing power. This is a definite limitation, as can be seen in the decidedly unreliable voice control systems found in cars.<\/p>\r\n\r\n\r\n\r\n<p>Soon MCUs will be able to run deep neural networks. This will allow them to run truly autonomous voice assistants that don\u2019t rely on network connectivity. Finally, we will have car voice control that doesn\u2019t rely on us speaking slowly, clearly, and with careful annunciation!<\/p>\r\n\r\n\r\n\r\n<h3 class=\"wp-block-heading\" id=\"h-intelligent-security-systems\">Intelligent security systems<\/h3>\r\n\r\n\r\n\r\n<p>My third prediction relates to a key problem in the modern world\u2014security. Sadly, we live in a world where there are constant terror threats. We are always asked to watch out for unattended bags or suspicious behaviour. But what if we could rely on artificial intelligence to be our eyes and ears?\u00a0<\/p>\r\n\r\n\r\n\r\n<p>Well, if you search the academic literature, you can find plenty of published articles looking at using deep learning for this. For instance, <a href=\"https:\/\/arxiv.org\/pdf\/1909.05776.pdf\">i-SAFE<\/a>, which uses fuzzy decision making and deep learning to spot suspicious activity in a video feed. With the increased capability of edge-ML, this feature will soon be embedded in CCTV systems and even home security systems.<\/p>\r\n\r\n\r\n\r\n<h2 class=\"wp-block-heading\" id=\"h-conclusions\">Conclusions<\/h2>\r\n\r\n\r\n\r\n<p>Over the past months, I have talked a lot about edge-Machine Learning. You have seen how it is enabling artificial intelligence applications right at the edge of the network. I gave you hands-on examples of voice control, face recognition, and gesture detection. Hopefully, these have shown you something of the requirements and capabilities of edge-ML.\u00a0<\/p>\r\n\r\n\r\n\r\n<p>As you have seen, this is a rapidly evolving field with more and more applications. We have touched on a few of these, and I am sure you will hear lots about them in future. I hope you have been inspired to try out some of the practical examples. Most importantly, I hope you have enjoyed learning about a truly cutting-edge area of machine learning.<\/p>\r\n","protected":false},"excerpt":{"rendered":"<p>Over the past few months, I have shown you why machine learning at the network edge is so essential. In this final article, we look back at why machine learning is needed and look at some of the real-world cases where it has already been transformative. Why is Machine Learning needed at the network edge?&#8230; <a class=\"more-link\" href=\"https:\/\/www.codemotion.com\/magazine\/ai-ml\/machine-learning\/machine-learning-network-edge\/\">Read more<\/a><\/p>\n","protected":false},"author":83,"featured_media":13262,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_editorskit_title_hidden":false,"_editorskit_reading_time":9,"_editorskit_is_block_options_detached":false,"_editorskit_block_options_position":"{}","_uag_custom_page_level_css":"","_genesis_hide_title":false,"_genesis_hide_breadcrumbs":false,"_genesis_hide_singular_image":false,"_genesis_hide_footer_widgets":false,"_genesis_custom_body_class":"","_genesis_custom_post_class":"","_genesis_layout":"","footnotes":""},"categories":[35],"tags":[],"collections":[],"class_list":{"0":"post-13065","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"has-post-thumbnail","7":"category-machine-learning","8":"entry"},"yoast_head":"<!-- This site is optimized with the Yoast SEO Premium plugin v26.9 (Yoast SEO v26.9) - https:\/\/yoast.com\/product\/yoast-seo-premium-wordpress\/ -->\n<title>Edge Machine Learning: Real-World Cases<\/title>\n<meta name=\"description\" content=\"Why is machine learning necessary and whaty are some of the real-world cases where it has already been transformative? Find out here.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.codemotion.com\/magazine\/ai-ml\/machine-learning\/machine-learning-network-edge\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"The Rise of Machine Learning at the Network Edge\" \/>\n<meta property=\"og:description\" content=\"Why is machine learning necessary and whaty are some of the real-world cases where it has already been transformative? Find out here.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.codemotion.com\/magazine\/ai-ml\/machine-learning\/machine-learning-network-edge\/\" \/>\n<meta property=\"og:site_name\" content=\"Codemotion Magazine\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/Codemotion.Italy\/\" \/>\n<meta property=\"article:published_time\" content=\"2021-01-11T08:00:00+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2023-06-23T13:18:49+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.codemotion.com\/magazine\/wp-content\/uploads\/2021\/01\/charles-deluvio-pjAH2Ax4uWk-unsplash_logo-Mouser-white.png\" \/>\n\t<meta property=\"og:image:width\" content=\"896\" \/>\n\t<meta property=\"og:image:height\" content=\"504\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"author\" content=\"Mark Patrick, Mouser Electronics\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@CodemotionIT\" \/>\n<meta name=\"twitter:site\" content=\"@CodemotionIT\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Mark Patrick, Mouser Electronics\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"11 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/www.codemotion.com\/magazine\/ai-ml\/machine-learning\/machine-learning-network-edge\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/www.codemotion.com\/magazine\/ai-ml\/machine-learning\/machine-learning-network-edge\/\"},\"author\":{\"name\":\"Mark Patrick, Mouser Electronics\",\"@id\":\"https:\/\/www.codemotion.com\/magazine\/#\/schema\/person\/664e4da6990fc1344a2299435a542654\"},\"headline\":\"The Rise of Machine Learning at the Network Edge\",\"datePublished\":\"2021-01-11T08:00:00+00:00\",\"dateModified\":\"2023-06-23T13:18:49+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/www.codemotion.com\/magazine\/ai-ml\/machine-learning\/machine-learning-network-edge\/\"},\"wordCount\":2270,\"publisher\":{\"@id\":\"https:\/\/www.codemotion.com\/magazine\/#organization\"},\"image\":{\"@id\":\"https:\/\/www.codemotion.com\/magazine\/ai-ml\/machine-learning\/machine-learning-network-edge\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/www.codemotion.com\/magazine\/wp-content\/uploads\/2021\/01\/charles-deluvio-pjAH2Ax4uWk-unsplash_logo-Mouser-white.png\",\"articleSection\":[\"Machine Learning\"],\"inLanguage\":\"en-US\"},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.codemotion.com\/magazine\/ai-ml\/machine-learning\/machine-learning-network-edge\/\",\"url\":\"https:\/\/www.codemotion.com\/magazine\/ai-ml\/machine-learning\/machine-learning-network-edge\/\",\"name\":\"Edge Machine Learning: Real-World Cases\",\"isPartOf\":{\"@id\":\"https:\/\/www.codemotion.com\/magazine\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/www.codemotion.com\/magazine\/ai-ml\/machine-learning\/machine-learning-network-edge\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/www.codemotion.com\/magazine\/ai-ml\/machine-learning\/machine-learning-network-edge\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/www.codemotion.com\/magazine\/wp-content\/uploads\/2021\/01\/charles-deluvio-pjAH2Ax4uWk-unsplash_logo-Mouser-white.png\",\"datePublished\":\"2021-01-11T08:00:00+00:00\",\"dateModified\":\"2023-06-23T13:18:49+00:00\",\"description\":\"Why is machine learning necessary and whaty are some of the real-world cases where it has already been transformative? Find out here.\",\"breadcrumb\":{\"@id\":\"https:\/\/www.codemotion.com\/magazine\/ai-ml\/machine-learning\/machine-learning-network-edge\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.codemotion.com\/magazine\/ai-ml\/machine-learning\/machine-learning-network-edge\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.codemotion.com\/magazine\/ai-ml\/machine-learning\/machine-learning-network-edge\/#primaryimage\",\"url\":\"https:\/\/www.codemotion.com\/magazine\/wp-content\/uploads\/2021\/01\/charles-deluvio-pjAH2Ax4uWk-unsplash_logo-Mouser-white.png\",\"contentUrl\":\"https:\/\/www.codemotion.com\/magazine\/wp-content\/uploads\/2021\/01\/charles-deluvio-pjAH2Ax4uWk-unsplash_logo-Mouser-white.png\",\"width\":896,\"height\":504,\"caption\":\"Machine Learning on the Network Edge\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.codemotion.com\/magazine\/ai-ml\/machine-learning\/machine-learning-network-edge\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/www.codemotion.com\/magazine\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"AI\/ML\",\"item\":\"https:\/\/www.codemotion.com\/magazine\/ai-ml\/\"},{\"@type\":\"ListItem\",\"position\":3,\"name\":\"Machine Learning\",\"item\":\"https:\/\/www.codemotion.com\/magazine\/ai-ml\/machine-learning\/\"},{\"@type\":\"ListItem\",\"position\":4,\"name\":\"The Rise of Machine Learning at the Network Edge\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.codemotion.com\/magazine\/#website\",\"url\":\"https:\/\/www.codemotion.com\/magazine\/\",\"name\":\"Codemotion Magazine\",\"description\":\"We code the future. Together\",\"publisher\":{\"@id\":\"https:\/\/www.codemotion.com\/magazine\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.codemotion.com\/magazine\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/www.codemotion.com\/magazine\/#organization\",\"name\":\"Codemotion\",\"url\":\"https:\/\/www.codemotion.com\/magazine\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.codemotion.com\/magazine\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/www.codemotion.com\/magazine\/wp-content\/uploads\/2019\/11\/codemotionlogo.png\",\"contentUrl\":\"https:\/\/www.codemotion.com\/magazine\/wp-content\/uploads\/2019\/11\/codemotionlogo.png\",\"width\":225,\"height\":225,\"caption\":\"Codemotion\"},\"image\":{\"@id\":\"https:\/\/www.codemotion.com\/magazine\/#\/schema\/logo\/image\/\"},\"sameAs\":[\"https:\/\/www.facebook.com\/Codemotion.Italy\/\",\"https:\/\/x.com\/CodemotionIT\"]},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.codemotion.com\/magazine\/#\/schema\/person\/664e4da6990fc1344a2299435a542654\",\"name\":\"Mark Patrick, Mouser Electronics\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.codemotion.com\/magazine\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/0d35fad9fee01e991637b67f54ae7cb8b001b5d2c1e4f7c1942b2105dad5a9bf?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/0d35fad9fee01e991637b67f54ae7cb8b001b5d2c1e4f7c1942b2105dad5a9bf?s=96&d=mm&r=g\",\"caption\":\"Mark Patrick, Mouser Electronics\"},\"url\":\"https:\/\/www.codemotion.com\/magazine\/author\/mark-patrick\/\"}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"Edge Machine Learning: Real-World Cases","description":"Why is machine learning necessary and whaty are some of the real-world cases where it has already been transformative? Find out here.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.codemotion.com\/magazine\/ai-ml\/machine-learning\/machine-learning-network-edge\/","og_locale":"en_US","og_type":"article","og_title":"The Rise of Machine Learning at the Network Edge","og_description":"Why is machine learning necessary and whaty are some of the real-world cases where it has already been transformative? Find out here.","og_url":"https:\/\/www.codemotion.com\/magazine\/ai-ml\/machine-learning\/machine-learning-network-edge\/","og_site_name":"Codemotion Magazine","article_publisher":"https:\/\/www.facebook.com\/Codemotion.Italy\/","article_published_time":"2021-01-11T08:00:00+00:00","article_modified_time":"2023-06-23T13:18:49+00:00","og_image":[{"width":896,"height":504,"url":"https:\/\/www.codemotion.com\/magazine\/wp-content\/uploads\/2021\/01\/charles-deluvio-pjAH2Ax4uWk-unsplash_logo-Mouser-white.png","type":"image\/png"}],"author":"Mark Patrick, Mouser Electronics","twitter_card":"summary_large_image","twitter_creator":"@CodemotionIT","twitter_site":"@CodemotionIT","twitter_misc":{"Written by":"Mark Patrick, Mouser Electronics","Est. reading time":"11 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/www.codemotion.com\/magazine\/ai-ml\/machine-learning\/machine-learning-network-edge\/#article","isPartOf":{"@id":"https:\/\/www.codemotion.com\/magazine\/ai-ml\/machine-learning\/machine-learning-network-edge\/"},"author":{"name":"Mark Patrick, Mouser Electronics","@id":"https:\/\/www.codemotion.com\/magazine\/#\/schema\/person\/664e4da6990fc1344a2299435a542654"},"headline":"The Rise of Machine Learning at the Network Edge","datePublished":"2021-01-11T08:00:00+00:00","dateModified":"2023-06-23T13:18:49+00:00","mainEntityOfPage":{"@id":"https:\/\/www.codemotion.com\/magazine\/ai-ml\/machine-learning\/machine-learning-network-edge\/"},"wordCount":2270,"publisher":{"@id":"https:\/\/www.codemotion.com\/magazine\/#organization"},"image":{"@id":"https:\/\/www.codemotion.com\/magazine\/ai-ml\/machine-learning\/machine-learning-network-edge\/#primaryimage"},"thumbnailUrl":"https:\/\/www.codemotion.com\/magazine\/wp-content\/uploads\/2021\/01\/charles-deluvio-pjAH2Ax4uWk-unsplash_logo-Mouser-white.png","articleSection":["Machine Learning"],"inLanguage":"en-US"},{"@type":"WebPage","@id":"https:\/\/www.codemotion.com\/magazine\/ai-ml\/machine-learning\/machine-learning-network-edge\/","url":"https:\/\/www.codemotion.com\/magazine\/ai-ml\/machine-learning\/machine-learning-network-edge\/","name":"Edge Machine Learning: Real-World Cases","isPartOf":{"@id":"https:\/\/www.codemotion.com\/magazine\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.codemotion.com\/magazine\/ai-ml\/machine-learning\/machine-learning-network-edge\/#primaryimage"},"image":{"@id":"https:\/\/www.codemotion.com\/magazine\/ai-ml\/machine-learning\/machine-learning-network-edge\/#primaryimage"},"thumbnailUrl":"https:\/\/www.codemotion.com\/magazine\/wp-content\/uploads\/2021\/01\/charles-deluvio-pjAH2Ax4uWk-unsplash_logo-Mouser-white.png","datePublished":"2021-01-11T08:00:00+00:00","dateModified":"2023-06-23T13:18:49+00:00","description":"Why is machine learning necessary and whaty are some of the real-world cases where it has already been transformative? Find out here.","breadcrumb":{"@id":"https:\/\/www.codemotion.com\/magazine\/ai-ml\/machine-learning\/machine-learning-network-edge\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.codemotion.com\/magazine\/ai-ml\/machine-learning\/machine-learning-network-edge\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.codemotion.com\/magazine\/ai-ml\/machine-learning\/machine-learning-network-edge\/#primaryimage","url":"https:\/\/www.codemotion.com\/magazine\/wp-content\/uploads\/2021\/01\/charles-deluvio-pjAH2Ax4uWk-unsplash_logo-Mouser-white.png","contentUrl":"https:\/\/www.codemotion.com\/magazine\/wp-content\/uploads\/2021\/01\/charles-deluvio-pjAH2Ax4uWk-unsplash_logo-Mouser-white.png","width":896,"height":504,"caption":"Machine Learning on the Network Edge"},{"@type":"BreadcrumbList","@id":"https:\/\/www.codemotion.com\/magazine\/ai-ml\/machine-learning\/machine-learning-network-edge\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.codemotion.com\/magazine\/"},{"@type":"ListItem","position":2,"name":"AI\/ML","item":"https:\/\/www.codemotion.com\/magazine\/ai-ml\/"},{"@type":"ListItem","position":3,"name":"Machine Learning","item":"https:\/\/www.codemotion.com\/magazine\/ai-ml\/machine-learning\/"},{"@type":"ListItem","position":4,"name":"The Rise of Machine Learning at the Network Edge"}]},{"@type":"WebSite","@id":"https:\/\/www.codemotion.com\/magazine\/#website","url":"https:\/\/www.codemotion.com\/magazine\/","name":"Codemotion Magazine","description":"We code the future. Together","publisher":{"@id":"https:\/\/www.codemotion.com\/magazine\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.codemotion.com\/magazine\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/www.codemotion.com\/magazine\/#organization","name":"Codemotion","url":"https:\/\/www.codemotion.com\/magazine\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.codemotion.com\/magazine\/#\/schema\/logo\/image\/","url":"https:\/\/www.codemotion.com\/magazine\/wp-content\/uploads\/2019\/11\/codemotionlogo.png","contentUrl":"https:\/\/www.codemotion.com\/magazine\/wp-content\/uploads\/2019\/11\/codemotionlogo.png","width":225,"height":225,"caption":"Codemotion"},"image":{"@id":"https:\/\/www.codemotion.com\/magazine\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.facebook.com\/Codemotion.Italy\/","https:\/\/x.com\/CodemotionIT"]},{"@type":"Person","@id":"https:\/\/www.codemotion.com\/magazine\/#\/schema\/person\/664e4da6990fc1344a2299435a542654","name":"Mark Patrick, Mouser Electronics","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.codemotion.com\/magazine\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/0d35fad9fee01e991637b67f54ae7cb8b001b5d2c1e4f7c1942b2105dad5a9bf?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/0d35fad9fee01e991637b67f54ae7cb8b001b5d2c1e4f7c1942b2105dad5a9bf?s=96&d=mm&r=g","caption":"Mark Patrick, Mouser Electronics"},"url":"https:\/\/www.codemotion.com\/magazine\/author\/mark-patrick\/"}]}},"featured_image_src":"https:\/\/www.codemotion.com\/magazine\/wp-content\/uploads\/2021\/01\/charles-deluvio-pjAH2Ax4uWk-unsplash_logo-Mouser-white-600x400.png","featured_image_src_square":"https:\/\/www.codemotion.com\/magazine\/wp-content\/uploads\/2021\/01\/charles-deluvio-pjAH2Ax4uWk-unsplash_logo-Mouser-white-600x504.png","author_info":{"display_name":"Mark Patrick, Mouser Electronics","author_link":"https:\/\/www.codemotion.com\/magazine\/author\/mark-patrick\/"},"uagb_featured_image_src":{"full":["https:\/\/www.codemotion.com\/magazine\/wp-content\/uploads\/2021\/01\/charles-deluvio-pjAH2Ax4uWk-unsplash_logo-Mouser-white.png",896,504,false],"thumbnail":["https:\/\/www.codemotion.com\/magazine\/wp-content\/uploads\/2021\/01\/charles-deluvio-pjAH2Ax4uWk-unsplash_logo-Mouser-white-150x150.png",150,150,true],"medium":["https:\/\/www.codemotion.com\/magazine\/wp-content\/uploads\/2021\/01\/charles-deluvio-pjAH2Ax4uWk-unsplash_logo-Mouser-white-300x169.png",300,169,true],"medium_large":["https:\/\/www.codemotion.com\/magazine\/wp-content\/uploads\/2021\/01\/charles-deluvio-pjAH2Ax4uWk-unsplash_logo-Mouser-white-768x432.png",768,432,true],"large":["https:\/\/www.codemotion.com\/magazine\/wp-content\/uploads\/2021\/01\/charles-deluvio-pjAH2Ax4uWk-unsplash_logo-Mouser-white.png",896,504,false],"1536x1536":["https:\/\/www.codemotion.com\/magazine\/wp-content\/uploads\/2021\/01\/charles-deluvio-pjAH2Ax4uWk-unsplash_logo-Mouser-white.png",896,504,false],"2048x2048":["https:\/\/www.codemotion.com\/magazine\/wp-content\/uploads\/2021\/01\/charles-deluvio-pjAH2Ax4uWk-unsplash_logo-Mouser-white.png",896,504,false],"small-home-featured":["https:\/\/www.codemotion.com\/magazine\/wp-content\/uploads\/2021\/01\/charles-deluvio-pjAH2Ax4uWk-unsplash_logo-Mouser-white.png",100,56,false],"sidebar-featured":["https:\/\/www.codemotion.com\/magazine\/wp-content\/uploads\/2021\/01\/charles-deluvio-pjAH2Ax4uWk-unsplash_logo-Mouser-white-180x128.png",180,128,true],"genesis-singular-images":["https:\/\/www.codemotion.com\/magazine\/wp-content\/uploads\/2021\/01\/charles-deluvio-pjAH2Ax4uWk-unsplash_logo-Mouser-white-896x504.png",896,504,true],"archive-featured":["https:\/\/www.codemotion.com\/magazine\/wp-content\/uploads\/2021\/01\/charles-deluvio-pjAH2Ax4uWk-unsplash_logo-Mouser-white-400x225.png",400,225,true],"gb-block-post-grid-landscape":["https:\/\/www.codemotion.com\/magazine\/wp-content\/uploads\/2021\/01\/charles-deluvio-pjAH2Ax4uWk-unsplash_logo-Mouser-white-600x400.png",600,400,true],"gb-block-post-grid-square":["https:\/\/www.codemotion.com\/magazine\/wp-content\/uploads\/2021\/01\/charles-deluvio-pjAH2Ax4uWk-unsplash_logo-Mouser-white-600x504.png",600,504,true]},"uagb_author_info":{"display_name":"Mark Patrick, Mouser Electronics","author_link":"https:\/\/www.codemotion.com\/magazine\/author\/mark-patrick\/"},"uagb_comment_info":0,"uagb_excerpt":"Over the past few months, I have shown you why machine learning at the network edge is so essential. In this final article, we look back at why machine learning is needed and look at some of the real-world cases where it has already been transformative. Why is Machine Learning needed at the network edge?&#8230;&hellip;","lang":"en","_links":{"self":[{"href":"https:\/\/www.codemotion.com\/magazine\/wp-json\/wp\/v2\/posts\/13065","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.codemotion.com\/magazine\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.codemotion.com\/magazine\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.codemotion.com\/magazine\/wp-json\/wp\/v2\/users\/83"}],"replies":[{"embeddable":true,"href":"https:\/\/www.codemotion.com\/magazine\/wp-json\/wp\/v2\/comments?post=13065"}],"version-history":[{"count":10,"href":"https:\/\/www.codemotion.com\/magazine\/wp-json\/wp\/v2\/posts\/13065\/revisions"}],"predecessor-version":[{"id":21570,"href":"https:\/\/www.codemotion.com\/magazine\/wp-json\/wp\/v2\/posts\/13065\/revisions\/21570"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.codemotion.com\/magazine\/wp-json\/wp\/v2\/media\/13262"}],"wp:attachment":[{"href":"https:\/\/www.codemotion.com\/magazine\/wp-json\/wp\/v2\/media?parent=13065"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.codemotion.com\/magazine\/wp-json\/wp\/v2\/categories?post=13065"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.codemotion.com\/magazine\/wp-json\/wp\/v2\/tags?post=13065"},{"taxonomy":"collections","embeddable":true,"href":"https:\/\/www.codemotion.com\/magazine\/wp-json\/wp\/v2\/collections?post=13065"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}