[{"data":1,"prerenderedAt":74},["ShallowReactive",2],{"i-material-symbols:language":3,"i-material-symbols:person":8,"i-mdi:instagram":10,"i-mdi:youtube":12,"i-ri:linkedin-fill":14,"i-ri:twitter-x-line":16,"i-ri:facebook-fill":18,"post-uncovering-the-mystery-of-deep-learning":20,"i-material-symbols:person-outline":68,"i-material-symbols:calendar-month":70,"i-mdi:schedule":72},{"left":4,"top":4,"width":5,"height":5,"rotate":4,"vFlip":6,"hFlip":6,"body":7},0,24,false,"\u003Cpath fill=\"currentColor\" d=\"M8.125 21.213q-1.825-.788-3.187-2.15t-2.15-3.188T2 11.988t.788-3.875t2.15-3.175t3.187-2.15T12.013 2t3.875.788t3.175 2.15t2.15 3.175t.787 3.875t-.787 3.887t-2.15 3.188t-3.175 2.15t-3.875.787t-3.888-.787M12 19.95q.65-.9 1.125-1.875T13.9 16h-3.8q.3 1.1.775 2.075T12 19.95m-2.6-.4q-.45-.825-.787-1.713T8.05 16H5.1q.725 1.25 1.813 2.175T9.4 19.55m5.2 0q1.4-.45 2.488-1.375T18.9 16h-2.95q-.225.95-.562 1.838T14.6 19.55M4.25 14h3.4q-.075-.5-.112-.987T7.5 12t.038-1.012T7.65 10h-3.4q-.125.5-.187.988T4 12t.063 1.013t.187.987m5.4 0h4.7q.075-.5.113-.987T14.5 12t-.038-1.012T14.35 10h-4.7q-.075.5-.112.988T9.5 12t.038 1.013t.112.987m6.7 0h3.4q.125-.5.188-.987T20 12t-.062-1.012T19.75 10h-3.4q.075.5.113.988T16.5 12t-.038 1.013t-.112.987m-.4-6h2.95q-.725-1.25-1.812-2.175T14.6 4.45q.45.825.788 1.713T15.95 8M10.1 8h3.8q-.3-1.1-.775-2.075T12 4.05q-.65.9-1.125 1.875T10.1 8m-5 0h2.95q.225-.95.563-1.838T9.4 4.45Q8 4.9 6.912 5.825T5.1 8\"\u002F>",{"left":4,"top":4,"width":5,"height":5,"rotate":4,"vFlip":6,"hFlip":6,"body":9},"\u003Cpath fill=\"currentColor\" d=\"M9.175 10.825Q8 9.65 8 8t1.175-2.825T12 4t2.825 1.175T16 8t-1.175 2.825T12 12t-2.825-1.175M4 20v-2.8q0-.85.438-1.562T5.6 14.55q1.55-.775 3.15-1.162T12 13t3.25.388t3.15 1.162q.725.375 1.163 1.088T20 17.2V20z\"\u002F>",{"left":4,"top":4,"width":5,"height":5,"rotate":4,"vFlip":6,"hFlip":6,"body":11},"\u003Cpath fill=\"currentColor\" d=\"M7.8 2h8.4C19.4 2 22 4.6 22 7.8v8.4a5.8 5.8 0 0 1-5.8 5.8H7.8C4.6 22 2 19.4 2 16.2V7.8A5.8 5.8 0 0 1 7.8 2m-.2 2A3.6 3.6 0 0 0 4 7.6v8.8C4 18.39 5.61 20 7.6 20h8.8a3.6 3.6 0 0 0 3.6-3.6V7.6C20 5.61 18.39 4 16.4 4zm9.65 1.5a1.25 1.25 0 0 1 1.25 1.25A1.25 1.25 0 0 1 17.25 8A1.25 1.25 0 0 1 16 6.75a1.25 1.25 0 0 1 1.25-1.25M12 7a5 5 0 0 1 5 5a5 5 0 0 1-5 5a5 5 0 0 1-5-5a5 5 0 0 1 5-5m0 2a3 3 0 0 0-3 3a3 3 0 0 0 3 3a3 3 0 0 0 3-3a3 3 0 0 0-3-3\"\u002F>",{"left":4,"top":4,"width":5,"height":5,"rotate":4,"vFlip":6,"hFlip":6,"body":13},"\u003Cpath fill=\"currentColor\" d=\"m10 15l5.19-3L10 9zm11.56-7.83c.13.47.22 1.1.28 1.9c.07.8.1 1.49.1 2.09L22 12c0 2.19-.16 3.8-.44 4.83c-.25.9-.83 1.48-1.73 1.73c-.47.13-1.33.22-2.65.28c-1.3.07-2.49.1-3.59.1L12 19c-4.19 0-6.8-.16-7.83-.44c-.9-.25-1.48-.83-1.73-1.73c-.13-.47-.22-1.1-.28-1.9c-.07-.8-.1-1.49-.1-2.09L2 12c0-2.19.16-3.8.44-4.83c.25-.9.83-1.48 1.73-1.73c.47-.13 1.33-.22 2.65-.28c1.3-.07 2.49-.1 3.59-.1L12 5c4.19 0 6.8.16 7.83.44c.9.25 1.48.83 1.73 1.73\"\u002F>",{"left":4,"top":4,"width":5,"height":5,"rotate":4,"vFlip":6,"hFlip":6,"body":15},"\u003Cpath fill=\"currentColor\" d=\"M6.94 5a2 2 0 1 1-4-.002a2 2 0 0 1 4 .002M7 8.48H3V21h4zm6.32 0H9.34V21h3.94v-6.57c0-3.66 4.77-4 4.77 0V21H22v-7.93c0-6.17-7.06-5.94-8.72-2.91z\"\u002F>",{"left":4,"top":4,"width":5,"height":5,"rotate":4,"vFlip":6,"hFlip":6,"body":17},"\u003Cpath fill=\"currentColor\" d=\"M10.488 14.651L15.25 21h7l-7.858-10.478L20.93 3h-2.65l-5.117 5.886L8.75 3h-7l7.51 10.015L2.32 21h2.65zM16.25 19L5.75 5h2l10.5 14z\"\u002F>",{"left":4,"top":4,"width":5,"height":5,"rotate":4,"vFlip":6,"hFlip":6,"body":19},"\u003Cpath fill=\"currentColor\" d=\"M14 13.5h2.5l1-4H14v-2c0-1.03 0-2 2-2h1.5V2.14c-.326-.043-1.557-.14-2.857-.14C11.928 2 10 3.657 10 6.7v2.8H7v4h3V22h4z\"\u002F>",{"postType":21,"id":22,"author":23,"date":26,"modified":27,"title":28,"slug":29,"seoTitle":30,"seoDescription":31,"excerpt":32,"trimmedExcerpt":33,"content":34,"readingTime":35,"featuredImage":36,"postCategory":41,"relatedPosts":46},"post",64232,{"id":24,"name":25},"author-0301142015","Canto","2024-01-31T18:36:56","2026-07-22T15:17:21","Deep learning explained: How AI models actually learn and what that means for marketing teams","uncovering-the-mystery-of-deep-learning","Demystifying deep learning and how it works","Get a sneak peek into exactly how deep learning works, including a comparison of the human brain vs AI neural networks and how AI is helping us today.","What is deep learning? Deep learning is a subset of machine learning that uses layered neural networks to recognize patterns in large datasets, improving its accuracy over time through repeated exposure to labeled training data. Unlike traditional rule-based programming, deep learning models automatically adjust their internal parameters based on feedback, enabling them to perform tasks […]","What is deep learning? Deep learning is a subset of machine learning that uses layered neural networks to recognize patterns...","\u003Ch2 class=\"wp-block-heading\" id=\"toc-1--what-is-deep-learning\">What is deep learning?\u003C\u002Fh2>\u003Cp class=\"wp-block-paragraph\">Deep learning is a subset of machine learning that uses layered neural networks to recognize patterns in large datasets, improving its accuracy over time through repeated exposure to labeled training data. Unlike traditional rule-based programming, deep learning models automatically adjust their internal parameters based on feedback, enabling them to perform tasks such as image recognition, language processing, and content classification. The more high-quality training data a model receives, the more reliable its outputs become.\u003C\u002Fp>\u003Cp class=\"wp-block-paragraph\">\u003Ca href=\"\u002Fglossary\u002Fmarketing-resource-management\u002F\">Marketing resource management\u003C\u002Fa> (MRM) combines tools and processes that enable marketing teams to plan, execute, and measure campaigns with greater efficiency — and deep learning is increasingly central to how those tools automate tagging, search, and content recommendations at scale.\u003C\u002Fp>\u003Ch2 class=\"wp-block-heading\" id=\"toc-2--understanding-deep-learning\">Understanding deep learning\u003C\u002Fh2>\u003Cp class=\"wp-block-paragraph\">By the time a child is five years old, they have absorbed a lot of information. But how does a five-year-old (we will call him little Johnny) develop an understanding of what a car looks like?\u003C\u002Fp>\u003Cp class=\"wp-block-paragraph\">Odds are that someone read him a children’s book containing a picture of a car. Johnny probably has been driven to see relatives, or the doctor, in the family car. Maybe he saw a children’s TV show with a car.\u003C\u002Fp>\u003Cp class=\"wp-block-paragraph\">All these data points formed a pathway in their brain that equates a car with that thing with four wheels. Each of those points were part of that five-year-old’s \u003Cem>training set\u003C\u002Fem>.\u003C\u002Fp>\u003Cfigure class=\"wp-block-image aligncenter\">\u003Cimg loading=\"lazy\" decoding=\"async\" width=\"880\" height=\"450\" src=\"\u002Fcdn\u002Fen\u002F2024\u002F01\u002F19183959\u002Flearning_with_labeled_images.jpg\" alt=\"Child learning with labeled images of a dog, car, airplane, and house over a green background.\" class=\"wp-image-64240\" srcset=\"\u002Fcdn\u002Fen\u002F2024\u002F01\u002F19183959\u002Flearning_with_labeled_images.jpg 880w, \u002Fcdn\u002Fen\u002F2024\u002F01\u002F19183959\u002Flearning_with_labeled_images-450x230.jpg 450w, \u002Fcdn\u002Fen\u002F2024\u002F01\u002F19183959\u002Flearning_with_labeled_images-768x393.jpg 768w\" \u002F>\u003C\u002Ffigure>\u003Cp class=\"wp-block-paragraph\">This learning process is not without errors! For example, let’s say you had a set of cards with the picture of an object (dog, car, airplane, house) on one side, and the word for it on the other. The first time through the deck, Johnny may say “cat!” when shown a photo of a \u003Cem>dog\u003C\u002Fem>. Once Johnny is corrected, the next time through the deck, he is likely to get it right.\u003C\u002Fp>\u003Cp class=\"wp-block-paragraph\">This is almost exactly how an AI model \u003Cem>learns\u003C\u002Fem> things.\u003C\u002Fp>\u003Cfigure class=\"wp-block-image aligncenter\">\u003Cimg loading=\"lazy\" decoding=\"async\" width=\"880\" height=\"450\" src=\"\u002Fcdn\u002Fen\u002F2024\u002F01\u002F19184000\u002Fbiological_neural_network.jpg\" alt=\"A biological neural network illustration of a man seeing and recognizing a car over a green background.\" class=\"wp-image-64238\" srcset=\"\u002Fcdn\u002Fen\u002F2024\u002F01\u002F19184000\u002Fbiological_neural_network.jpg 880w, \u002Fcdn\u002Fen\u002F2024\u002F01\u002F19184000\u002Fbiological_neural_network-450x230.jpg 450w, \u002Fcdn\u002Fen\u002F2024\u002F01\u002F19184000\u002Fbiological_neural_network-768x393.jpg 768w\" \u002F>\u003C\u002Ffigure>\u003Cp class=\"wp-block-paragraph\">The human brain is a neural network, with biological neurons. AI has a neural network, much the same.\u003C\u002Fp>\u003Ch2 class=\"wp-block-heading\" id=\"toc-3--how-ai-neural-networks-work\">How AI neural networks work\u003C\u002Fh2>\u003Cp class=\"wp-block-paragraph\">We can illustrate how an AI neural network works with some rows and columns of dots (we call those \u003Cem>hidden layers\u003C\u002Fem>), where each dot is connected to others and has a little math behind it (it can multiply any input by a number and add or subtract from any input by a number). You can think of the dots as neurons made of software.\u003C\u002Fp>\u003Cfigure class=\"wp-block-image aligncenter\">\u003Cimg loading=\"lazy\" decoding=\"async\" width=\"880\" height=\"450\" src=\"\u002Fcdn\u002Fen\u002F2024\u002F01\u002F19183958\u002Fdigital_neural_network_deep_learning.jpg\" alt=\"A digital neural network illustration of the input, hidden layers, and output neurons over a green background.\" class=\"wp-image-64242\" srcset=\"\u002Fcdn\u002Fen\u002F2024\u002F01\u002F19183958\u002Fdigital_neural_network_deep_learning.jpg 880w, \u002Fcdn\u002Fen\u002F2024\u002F01\u002F19183958\u002Fdigital_neural_network_deep_learning-450x230.jpg 450w, \u002Fcdn\u002Fen\u002F2024\u002F01\u002F19183958\u002Fdigital_neural_network_deep_learning-768x393.jpg 768w\" \u002F>\u003C\u002Ffigure>\u003Cp class=\"wp-block-paragraph\">Now, let’s ask the AI to identify an object like an airplane.\u003C\u002Fp>\u003Cfigure class=\"wp-block-image aligncenter\">\u003Cimg loading=\"lazy\" decoding=\"async\" width=\"880\" height=\"450\" src=\"\u002Fcdn\u002Fen\u002F2024\u002F01\u002F19184000\u002Fdeep_learning_airplace.jpg\" alt=\"Inputting an airplane photo into an AI model for training.\" class=\"wp-image-64237\" srcset=\"\u002Fcdn\u002Fen\u002F2024\u002F01\u002F19184000\u002Fdeep_learning_airplace.jpg 880w, \u002Fcdn\u002Fen\u002F2024\u002F01\u002F19184000\u002Fdeep_learning_airplace-450x230.jpg 450w, \u002Fcdn\u002Fen\u002F2024\u002F01\u002F19184000\u002Fdeep_learning_airplace-768x393.jpg 768w\" \u002F>\u003C\u002Ffigure>\u003Cp class=\"wp-block-paragraph\">At this point, the AI neural network model knows nothing. The math at each node is just a bunch of random numbers, kind of like a newborn baby that has seen no inputs yet. Given the random numbers in our model, the AI model is almost sure to answer incorrectly.\u003C\u002Fp>\u003Cfigure class=\"wp-block-image aligncenter\">\u003Cimg loading=\"lazy\" decoding=\"async\" width=\"880\" height=\"450\" src=\"\u002Fcdn\u002Fen\u002F2024\u002F01\u002F19183958\u002Fdeep_learning_incorrect_answer.jpg\" alt=\"An untrained AI model getting the wrong answer during training with an airplane photo over a green background.\" class=\"wp-image-64243\" srcset=\"\u002Fcdn\u002Fen\u002F2024\u002F01\u002F19183958\u002Fdeep_learning_incorrect_answer.jpg 880w, \u002Fcdn\u002Fen\u002F2024\u002F01\u002F19183958\u002Fdeep_learning_incorrect_answer-450x230.jpg 450w, \u002Fcdn\u002Fen\u002F2024\u002F01\u002F19183958\u002Fdeep_learning_incorrect_answer-768x393.jpg 768w\" \u002F>\u003C\u002Ffigure>\u003Cp class=\"wp-block-paragraph\">Remember when little Johnny told us cat when the right answer was dog? We corrected Johnny, so let’s do the same thing with AI and send a correction back through its network. The correction will slightly nudge the math at all the nodes towards the right answer and away from the wrong answer (called \u003Cem>backpropagation\u003C\u002Fem>):\u003C\u002Fp>\u003Cfigure class=\"wp-block-image aligncenter\">\u003Cimg loading=\"lazy\" decoding=\"async\" width=\"880\" height=\"450\" src=\"\u002Fcdn\u002Fen\u002F2024\u002F01\u002F19183959\u002Fdeep_learning_backpropagation.jpg\" alt=\"An illustration of an AI model learning the right answer by correcting the math on a few nodes and sending it back through over a green background.\" class=\"wp-image-64241\" srcset=\"\u002Fcdn\u002Fen\u002F2024\u002F01\u002F19183959\u002Fdeep_learning_backpropagation.jpg 880w, \u002Fcdn\u002Fen\u002F2024\u002F01\u002F19183959\u002Fdeep_learning_backpropagation-450x230.jpg 450w, \u002Fcdn\u002Fen\u002F2024\u002F01\u002F19183959\u002Fdeep_learning_backpropagation-768x393.jpg 768w\" \u002F>\u003C\u002Ffigure>\u003Cp class=\"wp-block-paragraph\">Now, to \u003Cem>train\u003C\u002Fem> our AI model in this example, we would need to send lots of photos of dogs, cars, airplanes, and houses, and we must send them through millions of times. We can consider this a massive training set, which means lots of photos that are \u003Cem>correctly\u003C\u002Fem> labelled as dogs, airplanes, or whatever we wish the AI to be trained on.\u003C\u002Fp>\u003Ccto-card white=\"true\" shadow=\"false\">\u003Ch3 class=\"wp-block-heading\">“Without a great training set, we have no chance of getting a useful AI model.”\u003C\u002Fh3>\u003C\u002Fcto-card>\u003Cp class=\"wp-block-paragraph\">Given a great training set and using advances in technology (with chips called graphics processing units or \u003Cem>GPUs\u003C\u002Fem>), we can quickly end up with an AI model that can correctly classify a picture it has never seen before as containing either a dog, car, airplane, or house!\u003C\u002Fp>\u003Cp class=\"wp-block-paragraph\">And, do it as well as a human can.\u003C\u002Fp>\u003Ch2 class=\"wp-block-heading\" id=\"toc-4--what-can-ai-help-us-with\">What can AI help us with?\u003C\u002Fh2>\u003Cp class=\"wp-block-paragraph\">Of course, we could train a new model to identify types of cancer, troubleshoot automobile issues, suggest new Amazon purchases, or solve lots of other problems we might care about.\u003C\u002Fp>\u003Cp class=\"wp-block-paragraph\">While the \u003Cem>neural networks\u003C\u002Fem> will improve over time, the reality is AI only works with a huge training set. For example, if you want to train a model to understand writing in English, then you better use a training set the size of all of Wikipedia!\u003C\u002Fp>\u003Cp class=\"wp-block-paragraph\">AI is good at recognizing (sometimes very subtle) patterns inside training sets. As an example, there is an AI model trained on slides of lung cancer, and it can identify if lung tissue is cancerous or not, and if it is, what type of cancer is involved. It can do it correctly about 96% of the time, which is roughly the same as the recognition rate of top oncologists. In some cases, it picks up on slide patterns so subtle that humans cannot see.\u003C\u002Fp>\u003Cp class=\"wp-block-paragraph\">\u003Cstrong>Bottom line:\u003C\u002Fstrong> AI models are only as good as the training set you use to develop them.\u003C\u002Fp>\u003Cp class=\"wp-block-paragraph\">And that is how \u003Cem>deep learning\u003C\u002Fem> works. Not much of a mystery, is it?\u003C\u002Fp>",4,{"url":37,"url_md":38,"alt":30,"height":39,"width":40},"https:\u002F\u002Fwww.canto.com\u002Fcdn\u002Fen\u002F2024\u002F01\u002F19183959\u002Fdemystifying_deep_learning.jpg","https:\u002F\u002Fwww.canto.com\u002Fcdn\u002Fen\u002F2024\u002F01\u002F19183959\u002Fdemystifying_deep_learning-450x225.jpg",600,1200,[42],{"id":43,"slug":43,"title":44,"path":45},"ai","Artificial Intelligence","\u002Fpost-category\u002Fai\u002F",[47,54,61],{"featuredImage":48,"postId":49,"slug":50,"title":51,"description":52,"path":53},"https:\u002F\u002Fwww.canto.com\u002Fcdn\u002Fen\u002F2020\u002F04\u002F19191912\u002Fai-advertising-450x311.jpg",44377,"ai-advertising","The most important ways AI is changing advertising","Artificial intelligence is a growing technological component that has unique benefits for companies. Check out how it's revolutionizing advertisements.","\u002Fblog\u002Fai-advertising\u002F",{"featuredImage":55,"postId":56,"slug":57,"title":58,"description":59,"path":60},"https:\u002F\u002Fwww.canto.com\u002Fcdn\u002Fen\u002F2023\u002F04\u002F19184132\u002Fai-content-creation-Feature-450x263.png",63506,"ai-content-creation","How to scale marketing programs using AI content creation","With AI content creation tools, marketers can quickly scale to deliver customized, personalized content to specific audiences to boost engagement.","\u002Fblog\u002Fai-content-creation\u002F",{"featuredImage":62,"postId":63,"slug":64,"title":65,"description":66,"path":67},"https:\u002F\u002Fwww.canto.com\u002Fcdn\u002Fen\u002F2022\u002F09\u002F19184045\u002FCanto_Blog-AI-creativity_feature-450x261.jpg",61999,"how-you-can-make-more-time-for-creativity-the-ai-ready-test","How You Can Make More Time For Creativity: The AI-Ready Test","What would happen if leaders and teams thought about our most-used apps like co-workers? Make more time for creativity using AI tech.","\u002Fblog\u002Fhow-you-can-make-more-time-for-creativity-the-ai-ready-test\u002F",{"left":4,"top":4,"width":5,"height":5,"rotate":4,"vFlip":6,"hFlip":6,"body":69},"\u003Cpath fill=\"currentColor\" d=\"M9.175 10.825Q8 9.65 8 8t1.175-2.825T12 4t2.825 1.175T16 8t-1.175 2.825T12 12t-2.825-1.175M4 20v-2.8q0-.85.438-1.562T5.6 14.55q1.55-.775 3.15-1.162T12 13t3.25.388t3.15 1.162q.725.375 1.163 1.088T20 17.2V20zm2-2h12v-.8q0-.275-.137-.5t-.363-.35q-1.35-.675-2.725-1.012T12 15t-2.775.338T6.5 16.35q-.225.125-.363.35T6 17.2zm7.413-8.587Q14 8.825 14 8t-.587-1.412T12 6t-1.412.588T10 8t.588 1.413T12 10t1.413-.587M12 18\"\u002F>",{"left":4,"top":4,"width":5,"height":5,"rotate":4,"vFlip":6,"hFlip":6,"body":71},"\u003Cpath fill=\"currentColor\" d=\"M12 14q-.425 0-.712-.288T11 13t.288-.712T12 12t.713.288T13 13t-.288.713T12 14m-4.712-.288Q7 13.426 7 13t.288-.712T8 12t.713.288T9 13t-.288.713T8 14t-.712-.288M16 14q-.425 0-.712-.288T15 13t.288-.712T16 12t.713.288T17 13t-.288.713T16 14m-4 4q-.425 0-.712-.288T11 17t.288-.712T12 16t.713.288T13 17t-.288.713T12 18m-4.712-.288Q7 17.426 7 17t.288-.712T8 16t.713.288T9 17t-.288.713T8 18t-.712-.288M16 18q-.425 0-.712-.288T15 17t.288-.712T16 16t.713.288T17 17t-.288.713T16 18M5 22q-.825 0-1.412-.587T3 20V6q0-.825.588-1.412T5 4h1V2h2v2h8V2h2v2h1q.825 0 1.413.588T21 6v14q0 .825-.587 1.413T19 22zm0-2h14V10H5z\"\u002F>",{"left":4,"top":4,"width":5,"height":5,"rotate":4,"vFlip":6,"hFlip":6,"body":73},"\u003Cpath fill=\"currentColor\" d=\"M12 20a8 8 0 0 0 8-8a8 8 0 0 0-8-8a8 8 0 0 0-8 8a8 8 0 0 0 8 8m0-18a10 10 0 0 1 10 10a10 10 0 0 1-10 10C6.47 22 2 17.5 2 12A10 10 0 0 1 12 2m.5 5v5.25l4.5 2.67l-.75 1.23L11 13V7z\"\u002F>",1789621303752]