Name: Towards AI Legal Name: Towards AI, Inc. Description: Towards AI is the world's leading artificial intelligence (AI) and technology publication. Read by thought-leaders and decision-makers around the world. Phone Number: +1-650-246-9381 Email: pub@towardsai.net
228 Park Avenue South New York, NY 10003 United States
Website: Publisher: https://towardsai.net/#publisher Diversity Policy: https://towardsai.net/about Ethics Policy: https://towardsai.net/about Masthead: https://towardsai.net/about
Name: Towards AI Legal Name: Towards AI, Inc. Description: Towards AI is the world's leading artificial intelligence (AI) and technology publication. Founders: Roberto Iriondo, , Job Title: Co-founder and Advisor Works for: Towards AI, Inc. Follow Roberto: X, LinkedIn, GitHub, Google Scholar, Towards AI Profile, Medium, ML@CMU, FreeCodeCamp, Crunchbase, Bloomberg, Roberto Iriondo, Generative AI Lab, Generative AI Lab Denis Piffaretti, Job Title: Co-founder Works for: Towards AI, Inc. Louie Peters, Job Title: Co-founder Works for: Towards AI, Inc. Louis-François Bouchard, Job Title: Co-founder Works for: Towards AI, Inc. Cover:
Towards AI Cover
Logo:
Towards AI Logo
Areas Served: Worldwide Alternate Name: Towards AI, Inc. Alternate Name: Towards AI Co. Alternate Name: towards ai Alternate Name: towardsai Alternate Name: towards.ai Alternate Name: tai Alternate Name: toward ai Alternate Name: toward.ai Alternate Name: Towards AI, Inc. Alternate Name: towardsai.net Alternate Name: pub.towardsai.net
5 stars – based on 497 reviews

Frequently Used, Contextual References

TODO: Remember to copy unique IDs whenever it needs used. i.e., URL: 304b2e42315e

Resources

Take our 85+ lesson From Beginner to Advanced LLM Developer Certification: From choosing a project to deploying a working product this is the most comprehensive and practical LLM course out there!

Publication

The Architecture and Implementation of LeNet-5
Deep Learning

The Architecture and Implementation of LeNet-5

Last Updated on January 6, 2023 by Editorial Team

Last Updated on July 30, 2020 by Editorial Team

Author(s): Vaibhav Khandelwal

Deep Learning

Demystifying the oldest Neural Network Architecture of LeNet-5

Photo from Faz.net

This very old neural network architecture was developed in 1998 by a French-American computer scientist Yann André LeCun, Leon Bottou, Yoshua Bengio, and Patrick Haffner. This architecture was developed for the recognition of handwritten and machine-printed characters. It is the basis of other deep learning models.

Original Image published in [LeCun et al., 1998]

The architecture consists of a total of 7 layers consisting- 2 sets of Convolution layers and 2 sets of Average pooling layers which are followed by a flattening convolution layer. After that, we have 2 dense fully connected layers and finally a softmax classifier.

Input Layer

If we take a standard MNIST image for our understanding then we have an input of (32×32) grayscale image which passes through the first convolution layer with the 6 feature maps or filters having the size of (5×5) kernel and with a stride as 1. The values of the input pixels are normalized so that the white background and foreground black corresponds to -0.1 and 1.175 respectively, making mean approximately as 0 and the variance approximately as 1.

This input layer is not counted under network structure of LeNet-5 as traditionally, the input layer wasn’t considered as one of the network hierarchy.

First Layer

The result of the convolution of an input image with 6 filters has to lead to the change in dimension from (32x32x1) to (28x28x6) and we get our first layer. So, 1 channel is changed to 6 channels as 6 filters are applied to our input image. Also, the image size has been reduced as a result of zero paddings with a kernel size of (5×5).

Image by author

> Calculations for the First Layer

  • Filter size = f = 5 x 5
  • No. of filters = 6
  • Strides = S = 1
  • Padding = P = 0
  • Output featuremap size = 28 x 28
  • No. of neurons = 28*28*6 = 4,704

In Convolution, filter values are trainable parameters.

  • No. of learning parameters = (Weights + Bias )per filter * No. of filters

= (5 * 5 + 1) * 6 = 156

where, 5 * 5 = 25 are unit parameters and 1 bias per filter, and we have a total of 6 filters

  • No. of connections = 156 * 28 * 28 = 1,22,304

> Detailed description:

  1. The first convolution operation is applied on the input image (using 6 convolution kernels of size 5 x 5) to obtain 6 C1 feature maps (6 feature maps each of size 28 x 28), where size is obtained by (N-f+2P)/S+1, but as here P=0 and S=1, hence we are using N-f+1 throughout the content. Therefore, the output size after the convolution is 32–5 + 1 = 28.
  2. Let’s take a look at the numbers of parameters that are needed. The size of the convolution kernel is 5 x 5, and there are 6 * (5 * 5 + 1) = 156 parameters in total, where +1 indicates that the kernel has a bias.
  3. For the convolutional layer C1, each pixel in C1 is connected to 5 * 5 pixels and 1 bias, so there are 156 * 28 * 28 = 122304 connections in total. Though there are 1,22,304 connections, we only need 156 parameters to be learned, mainly through weight sharing.

Second Layer

In the second layer, we implemented an average pooling layer with a filter size of (2×2) and a stride of 2. So, the resultant image dimension will decrease to (14x14x6). Here each unit in each feature map is connected to (2 x 2) neighborhood in the corresponding feature map in C1.

Image by author

> Calculations for the Second Layer

  • Filter size = f = 2 x 2
  • No. of filters = 6
  • Strides = S = 2
  • Padding = P = 0
  • Output feature map size = 14 x 14
  • No. of neurons = 14*14*6 = 1,176

The 4 inputs are added to a unit in S2 from the corresponding feature map in C1 , then multiplied by a trainable coefficient, and added a trainable bias to it. The result is then passed through a sigmoidal activation function and we get the result Q

Image by author
  • No. of learning parameters = (Coefficient + Bias ) * No. of filters

= (1+ 1) * 6 = 12

where, the first 1 is the weight of the 2 x 2 receptive field corresponding to the pooling, and the second 1 is the bias.

  • No. of connections = (2*2 + 1)*14*14*6 = 5,880

> Detailed description:

  1. The pooling operation is followed immediately after the first convolution. Pooling is performed using 2 * 2 kernels, and 6 S2 feature maps of 14 * 14 are obtained.
  2. The pooling layer of S2 is the average of the pixels in the 2 * 2 area in C1 multiplied by a weight coefficient plus an offset or bias, and then the result is mapped again.
  3. So each pooling core has two training parameters, and thus in total there are 2*6 = 12 training parameters, but there are 5*14*14*6 = 5880 connections.

Third Layer

If we proceed further to the third layer, we are applying 16 filters with a kernel size of (5×5) to S2 resulting in a convolution layer C3 with 16 feature maps. This convolution results in changing the dimension of the image from (14 x 14 x 6) in S2 to (10 x 10 x 16) in C3.

Image by author

> Calculations for the Third Layer

  • Filter size = f = 5 x 5
  • No. of filters = 16
  • Strides = S = 1
  • Padding = P = 0
  • Output feature map size = 10 x 10
  • No. of neurons = 10*10*16 = 1,600

As here we can see that input i.e. S2 has 6 layers and the output i.e. C3 has 16 layers. Therefore we can not directly map each input layer to the output layer. So due to this, each unit in each feature map i.e. C3 is connected to several (5 x 5) neighborhoods at identical locations in a subset of S2’s feature maps.

The combination of different input feature maps selection from S2 will allow more new features to be extracted.

The different combinations of feature maps taken from S2 are shown in the figure below:

  1. Taking inputs from every contiguous subset of 3 feature maps from S2:- First 6 convolution layers of C3 are made with this combination.
  2. Taking inputs from every contiguous subset of 4 feature maps from S2:- Next 6 convolution layers of C3 are made with this combination.
  3. Taking inputs from the discontinuous subset of 4 feature maps from S2:- Next 3 layers of C3 were made with this combination.
  4. Taking all the feature maps:- The last layer of C3 is made with this combination.
Original Image published in [LeCun et al., 1998]
  • No. of learning parameters = (Parameters in combination type-1) + (Parameters in combination type-2) + (Parameters in combination type-3) + (Parameters in combination type-4)

= [6 * (5*5*3 + 1)] + [6 * (5*5*4 + 1)] + [3 * (5*5*4 + 1)] + [1 * (5*5*6 + 1)]

= 456 + 606 + 303 + 151 = 1516

NOTE:- In the above calculation the numbers 3, 4, 4, 6 used with 5*5 in the parenthesis are basically the depth.

  • No. of connections = 1516 * (10*10)= 1,51,600

Fourth Layer

In the fourth layer, we’ll again apply the average pooling layer with the filter size as (2×2) and a stride of 2. So, the resultant image has a resultant of the average pool which will be of the dimension (5x5x16). Here each unit in each feature map of S4 is connected to (2 x 2) neighborhood in the corresponding feature map in C3.

Image by author

> Calculations for Fourth Layer

  • Filter size = f = 2 x 2
  • No. of filters = 16
  • Strides = S = 2
  • Padding = P = 0
  • Output feature map size = 5 x 5
  • No. of neurons = 5*5*16 = 400
  • No. of learning parameters = (Coefficient + Bias ) * No. of filters

= (1+ 1) * 16 = 32

where, the first 1 is the weight of the 2 x 2 receptive field corresponding to the pooling, and the second 1 is the bias.

  • No. of connections = (2*2 + 1)*5*5*16 = 2,000

This completes 2 convolution operations and 2 pooling operations.

Fifth Layer

In the fifth layer, we have a fully connected Convolution layer C5 that has 120 neuron units, and each unit of C5 is connected to (5 x 5) neighborhood on all 16 of S4’s feature maps i.e. every unit of C5 is connected to all the feature maps of S4 and, thus C5 is known as Fully Connected Convolution Layer.

C5 is named as “Fully connected Convolution Layer” instead of simply “Fully connected layer” because if input size to the LeNet-5 is increased keeping everything else constant, the dimension of feature maps in C5 layer would be greater than (1 x 1).

So in the fourth layer, the resulting dimensions are (5x5x16), so the total nodes are 5x5x16 = 400 neurons. That means, 400 nodes are connected to 120 nodes as a dense fully connected network.

Image by author

> Calculations for the Fifth Layer

  • Filter size = f = 5 x 5
  • No. of filters = 120
  • Strides = S = 1
  • Padding = P = 0
  • Output feature map size = 1 x 1
  • No. of neurons = 1*1*120 = 120
  • No. of learning parameters = (5*5*16 + 1)*120 = 48,120
  • No. of connections = 48,120*1*1 = 48,120

Sixth Layer

The Sixth layer F6 consists of 84 neurons Fully connected with C5. Here dot product between the input vector and weight vector is performed and then bias is added to it. The result is then passed through a sigmoidal activation function.

Image by author

> Calculations for the Sixth Layer

  • Input: C5 with 120 neurons
  • Output: F6 with 84 neurons
  • No. of learning parameters = (120*84) + 84 = 10,164

The number of neurons in the F6 layer is chosen as 84, corresponding to a 7 x 12 bitmap, -1 means white, 1 means black, so the black and white of the bitmap of each symbol corresponds to a code. Such a representation is useful for recognizing strings of characters taken from the printable ASCII set. The characters that look similar and confusing as Uppercase O, 0, and lowercase O will have the same output codes.

The ASCII encoding set is as follows:

Original Image published in [LeCun et al., 1998]

And finally, we have a fully connected softmax output layer with 10 possible values corresponding to the digits from 0 to 9.

Image by author

So we have “softmax activation” function on the output layer and other layers which we saw have “tanh” as the activation function as softmax will give the probability of occurance each output class at the end.

We are now venturing into coding territory.

Implementation of LeNet-5 using Keras

Before we start implementing the LeNet-5 through code, there are few key points to be kept in mind:

  1. The input used by LeCun was of the size (32 x 32) but as we will be using the MNIST dataset, so the image size in this dataset is (28 x 28). Thus, the input size we’ll be having is (28 x 28).
  2. When LeCun applied the third convolution i.e. C5, the input size was(5 x 5) but as from the initial only our input size to the network is less as compared to what LeCun took and hence, the input size for C5 in our case would be (4 x 4) and applying convolution to this input with (5 x 5) filter would result in a negative dimension size which is not possible and hence we’ll apply Flatten() after S4.

Importing Libraries

Loading the dataset and performing train-test split

Checking the sizes of train and test split

The output of the above code will be as follows:

Shapes of train and test split

Performing reshaping operations- Converting into 4-D

Normalizing the values of the image- Converting in between 0 and 1

One-hot encoding the labels

Building the Model Architecture

Summary of the model

  • There are approx 45 thousand trainable parameters here as can be seen from the subsequent image.
Model Summary

Compilation of the model

And finally, a bit on evaluating your model.

Finding the loss and accuracy of the model

The output of loss and accuracy is as follows:

Loss and Accuracy of the model- Image by author

📌 To get the complete code of LeNet-5 or any other network visit my GitHub repository.

References:

[1] Yann LeCun, Gradient-Based Learning Applied to Document Recognition(1998), Proc of the IEEE(1998)

Thanks for reading. Hope this blog would have helped you with both the coding and understanding of the architecture. 😃


The Architecture and Implementation of LeNet-5 was originally published in Towards AI — Multidisciplinary Science Journal on Medium, where people are continuing the conversation by highlighting and responding to this story.

Published via Towards AI

Feedback ↓

Sign Up for the Course
`; } else { console.error('Element with id="subscribe" not found within the page with class "home".'); } } }); // Remove duplicate text from articles /* Backup: 09/11/24 function removeDuplicateText() { const elements = document.querySelectorAll('h1, h2, h3, h4, h5, strong'); // Select the desired elements const seenTexts = new Set(); // A set to keep track of seen texts const tagCounters = {}; // Object to track instances of each tag elements.forEach(el => { const tagName = el.tagName.toLowerCase(); // Get the tag name (e.g., 'h1', 'h2', etc.) // Initialize a counter for each tag if not already done if (!tagCounters[tagName]) { tagCounters[tagName] = 0; } // Only process the first 10 elements of each tag type if (tagCounters[tagName] >= 2) { return; // Skip if the number of elements exceeds 10 } const text = el.textContent.trim(); // Get the text content const words = text.split(/\s+/); // Split the text into words if (words.length >= 4) { // Ensure at least 4 words const significantPart = words.slice(0, 5).join(' '); // Get first 5 words for matching // Check if the text (not the tag) has been seen before if (seenTexts.has(significantPart)) { // console.log('Duplicate found, removing:', el); // Log duplicate el.remove(); // Remove duplicate element } else { seenTexts.add(significantPart); // Add the text to the set } } tagCounters[tagName]++; // Increment the counter for this tag }); } removeDuplicateText(); */ // Remove duplicate text from articles function removeDuplicateText() { const elements = document.querySelectorAll('h1, h2, h3, h4, h5, strong'); // Select the desired elements const seenTexts = new Set(); // A set to keep track of seen texts const tagCounters = {}; // Object to track instances of each tag // List of classes to be excluded const excludedClasses = ['medium-author', 'post-widget-title']; elements.forEach(el => { // Skip elements with any of the excluded classes if (excludedClasses.some(cls => el.classList.contains(cls))) { return; // Skip this element if it has any of the excluded classes } const tagName = el.tagName.toLowerCase(); // Get the tag name (e.g., 'h1', 'h2', etc.) // Initialize a counter for each tag if not already done if (!tagCounters[tagName]) { tagCounters[tagName] = 0; } // Only process the first 10 elements of each tag type if (tagCounters[tagName] >= 10) { return; // Skip if the number of elements exceeds 10 } const text = el.textContent.trim(); // Get the text content const words = text.split(/\s+/); // Split the text into words if (words.length >= 4) { // Ensure at least 4 words const significantPart = words.slice(0, 5).join(' '); // Get first 5 words for matching // Check if the text (not the tag) has been seen before if (seenTexts.has(significantPart)) { // console.log('Duplicate found, removing:', el); // Log duplicate el.remove(); // Remove duplicate element } else { seenTexts.add(significantPart); // Add the text to the set } } tagCounters[tagName]++; // Increment the counter for this tag }); } removeDuplicateText(); //Remove unnecessary text in blog excerpts document.querySelectorAll('.blog p').forEach(function(paragraph) { // Replace the unwanted text pattern for each paragraph paragraph.innerHTML = paragraph.innerHTML .replace(/Author\(s\): [\w\s]+ Originally published on Towards AI\.?/g, '') // Removes 'Author(s): XYZ Originally published on Towards AI' .replace(/This member-only story is on us\. Upgrade to access all of Medium\./g, ''); // Removes 'This member-only story...' }); //Load ionic icons and cache them if ('localStorage' in window && window['localStorage'] !== null) { const cssLink = 'https://code.ionicframework.com/ionicons/2.0.1/css/ionicons.min.css'; const storedCss = localStorage.getItem('ionicons'); if (storedCss) { loadCSS(storedCss); } else { fetch(cssLink).then(response => response.text()).then(css => { localStorage.setItem('ionicons', css); loadCSS(css); }); } } function loadCSS(css) { const style = document.createElement('style'); style.innerHTML = css; document.head.appendChild(style); } //Remove elements from imported content automatically function removeStrongFromHeadings() { const elements = document.querySelectorAll('h1, h2, h3, h4, h5, h6, span'); elements.forEach(el => { const strongTags = el.querySelectorAll('strong'); strongTags.forEach(strongTag => { while (strongTag.firstChild) { strongTag.parentNode.insertBefore(strongTag.firstChild, strongTag); } strongTag.remove(); }); }); } removeStrongFromHeadings(); "use strict"; window.onload = () => { /* //This is an object for each category of subjects and in that there are kewords and link to the keywods let keywordsAndLinks = { //you can add more categories and define their keywords and add a link ds: { keywords: [ //you can add more keywords here they are detected and replaced with achor tag automatically 'data science', 'Data science', 'Data Science', 'data Science', 'DATA SCIENCE', ], //we will replace the linktext with the keyword later on in the code //you can easily change links for each category here //(include class="ml-link" and linktext) link: 'linktext', }, ml: { keywords: [ //Add more keywords 'machine learning', 'Machine learning', 'Machine Learning', 'machine Learning', 'MACHINE LEARNING', ], //Change your article link (include class="ml-link" and linktext) link: 'linktext', }, ai: { keywords: [ 'artificial intelligence', 'Artificial intelligence', 'Artificial Intelligence', 'artificial Intelligence', 'ARTIFICIAL INTELLIGENCE', ], //Change your article link (include class="ml-link" and linktext) link: 'linktext', }, nl: { keywords: [ 'NLP', 'nlp', 'natural language processing', 'Natural Language Processing', 'NATURAL LANGUAGE PROCESSING', ], //Change your article link (include class="ml-link" and linktext) link: 'linktext', }, des: { keywords: [ 'data engineering services', 'Data Engineering Services', 'DATA ENGINEERING SERVICES', ], //Change your article link (include class="ml-link" and linktext) link: 'linktext', }, td: { keywords: [ 'training data', 'Training Data', 'training Data', 'TRAINING DATA', ], //Change your article link (include class="ml-link" and linktext) link: 'linktext', }, ias: { keywords: [ 'image annotation services', 'Image annotation services', 'image Annotation services', 'image annotation Services', 'Image Annotation Services', 'IMAGE ANNOTATION SERVICES', ], //Change your article link (include class="ml-link" and linktext) link: 'linktext', }, l: { keywords: [ 'labeling', 'labelling', ], //Change your article link (include class="ml-link" and linktext) link: 'linktext', }, pbp: { keywords: [ 'previous blog posts', 'previous blog post', 'latest', ], //Change your article link (include class="ml-link" and linktext) link: 'linktext', }, mlc: { keywords: [ 'machine learning course', 'machine learning class', ], //Change your article link (include class="ml-link" and linktext) link: 'linktext', }, }; //Articles to skip let articleIdsToSkip = ['post-2651', 'post-3414', 'post-3540']; //keyword with its related achortag is recieved here along with article id function searchAndReplace(keyword, anchorTag, articleId) { //selects the h3 h4 and p tags that are inside of the article let content = document.querySelector(`#${articleId} .entry-content`); //replaces the "linktext" in achor tag with the keyword that will be searched and replaced let newLink = anchorTag.replace('linktext', keyword); //regular expression to search keyword var re = new RegExp('(' + keyword + ')', 'g'); //this replaces the keywords in h3 h4 and p tags content with achor tag content.innerHTML = content.innerHTML.replace(re, newLink); } function articleFilter(keyword, anchorTag) { //gets all the articles var articles = document.querySelectorAll('article'); //if its zero or less then there are no articles if (articles.length > 0) { for (let x = 0; x < articles.length; x++) { //articles to skip is an array in which there are ids of articles which should not get effected //if the current article's id is also in that array then do not call search and replace with its data if (!articleIdsToSkip.includes(articles[x].id)) { //search and replace is called on articles which should get effected searchAndReplace(keyword, anchorTag, articles[x].id, key); } else { console.log( `Cannot replace the keywords in article with id ${articles[x].id}` ); } } } else { console.log('No articles found.'); } } let key; //not part of script, added for (key in keywordsAndLinks) { //key is the object in keywords and links object i.e ds, ml, ai for (let i = 0; i < keywordsAndLinks[key].keywords.length; i++) { //keywordsAndLinks[key].keywords is the array of keywords for key (ds, ml, ai) //keywordsAndLinks[key].keywords[i] is the keyword and keywordsAndLinks[key].link is the link //keyword and link is sent to searchreplace where it is then replaced using regular expression and replace function articleFilter( keywordsAndLinks[key].keywords[i], keywordsAndLinks[key].link ); } } function cleanLinks() { // (making smal functions is for DRY) this function gets the links and only keeps the first 2 and from the rest removes the anchor tag and replaces it with its text function removeLinks(links) { if (links.length > 1) { for (let i = 2; i < links.length; i++) { links[i].outerHTML = links[i].textContent; } } } //arrays which will contain all the achor tags found with the class (ds-link, ml-link, ailink) in each article inserted using search and replace let dslinks; let mllinks; let ailinks; let nllinks; let deslinks; let tdlinks; let iaslinks; let llinks; let pbplinks; let mlclinks; const content = document.querySelectorAll('article'); //all articles content.forEach((c) => { //to skip the articles with specific ids if (!articleIdsToSkip.includes(c.id)) { //getting all the anchor tags in each article one by one dslinks = document.querySelectorAll(`#${c.id} .entry-content a.ds-link`); mllinks = document.querySelectorAll(`#${c.id} .entry-content a.ml-link`); ailinks = document.querySelectorAll(`#${c.id} .entry-content a.ai-link`); nllinks = document.querySelectorAll(`#${c.id} .entry-content a.ntrl-link`); deslinks = document.querySelectorAll(`#${c.id} .entry-content a.des-link`); tdlinks = document.querySelectorAll(`#${c.id} .entry-content a.td-link`); iaslinks = document.querySelectorAll(`#${c.id} .entry-content a.ias-link`); mlclinks = document.querySelectorAll(`#${c.id} .entry-content a.mlc-link`); llinks = document.querySelectorAll(`#${c.id} .entry-content a.l-link`); pbplinks = document.querySelectorAll(`#${c.id} .entry-content a.pbp-link`); //sending the anchor tags list of each article one by one to remove extra anchor tags removeLinks(dslinks); removeLinks(mllinks); removeLinks(ailinks); removeLinks(nllinks); removeLinks(deslinks); removeLinks(tdlinks); removeLinks(iaslinks); removeLinks(mlclinks); removeLinks(llinks); removeLinks(pbplinks); } }); } //To remove extra achor tags of each category (ds, ml, ai) and only have 2 of each category per article cleanLinks(); */ //Recommended Articles var ctaLinks = [ /* ' ' + '

Subscribe to our AI newsletter!

' + */ '

Take our 85+ lesson From Beginner to Advanced LLM Developer Certification: From choosing a project to deploying a working product this is the most comprehensive and practical LLM course out there!

'+ '

Towards AI has published Building LLMs for Production—our 470+ page guide to mastering LLMs with practical projects and expert insights!

' + '
' + '' + '' + '

Note: Content contains the views of the contributing authors and not Towards AI.
Disclosure: This website may contain sponsored content and affiliate links.

' + 'Discover Your Dream AI Career at Towards AI Jobs' + '

Towards AI has built a jobs board tailored specifically to Machine Learning and Data Science Jobs and Skills. Our software searches for live AI jobs each hour, labels and categorises them and makes them easily searchable. Explore over 10,000 live jobs today with Towards AI Jobs!

' + '
' + '

🔥 Recommended Articles 🔥

' + 'Why Become an LLM Developer? Launching Towards AI’s New One-Stop Conversion Course'+ 'Testing Launchpad.sh: A Container-based GPU Cloud for Inference and Fine-tuning'+ 'The Top 13 AI-Powered CRM Platforms
' + 'Top 11 AI Call Center Software for 2024
' + 'Learn Prompting 101—Prompt Engineering Course
' + 'Explore Leading Cloud Providers for GPU-Powered LLM Training
' + 'Best AI Communities for Artificial Intelligence Enthusiasts
' + 'Best Workstations for Deep Learning
' + 'Best Laptops for Deep Learning
' + 'Best Machine Learning Books
' + 'Machine Learning Algorithms
' + 'Neural Networks Tutorial
' + 'Best Public Datasets for Machine Learning
' + 'Neural Network Types
' + 'NLP Tutorial
' + 'Best Data Science Books
' + 'Monte Carlo Simulation Tutorial
' + 'Recommender System Tutorial
' + 'Linear Algebra for Deep Learning Tutorial
' + 'Google Colab Introduction
' + 'Decision Trees in Machine Learning
' + 'Principal Component Analysis (PCA) Tutorial
' + 'Linear Regression from Zero to Hero
'+ '

', /* + '

Join thousands of data leaders on the AI newsletter. It’s free, we don’t spam, and we never share your email address. Keep up to date with the latest work in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

',*/ ]; var replaceText = { '': '', '': '', '
': '
' + ctaLinks + '
', }; Object.keys(replaceText).forEach((txtorig) => { //txtorig is the key in replacetext object const txtnew = replaceText[txtorig]; //txtnew is the value of the key in replacetext object let entryFooter = document.querySelector('article .entry-footer'); if (document.querySelectorAll('.single-post').length > 0) { //console.log('Article found.'); const text = entryFooter.innerHTML; entryFooter.innerHTML = text.replace(txtorig, txtnew); } else { // console.log('Article not found.'); //removing comment 09/04/24 } }); var css = document.createElement('style'); css.type = 'text/css'; css.innerHTML = '.post-tags { display:none !important } .article-cta a { font-size: 18px; }'; document.body.appendChild(css); //Extra //This function adds some accessibility needs to the site. function addAlly() { // In this function JQuery is replaced with vanilla javascript functions const imgCont = document.querySelector('.uw-imgcont'); imgCont.setAttribute('aria-label', 'AI news, latest developments'); imgCont.title = 'AI news, latest developments'; imgCont.rel = 'noopener'; document.querySelector('.page-mobile-menu-logo a').title = 'Towards AI Home'; document.querySelector('a.social-link').rel = 'noopener'; document.querySelector('a.uw-text').rel = 'noopener'; document.querySelector('a.uw-w-branding').rel = 'noopener'; document.querySelector('.blog h2.heading').innerHTML = 'Publication'; const popupSearch = document.querySelector$('a.btn-open-popup-search'); popupSearch.setAttribute('role', 'button'); popupSearch.title = 'Search'; const searchClose = document.querySelector('a.popup-search-close'); searchClose.setAttribute('role', 'button'); searchClose.title = 'Close search page'; // document // .querySelector('a.btn-open-popup-search') // .setAttribute( // 'href', // 'https://medium.com/towards-artificial-intelligence/search' // ); } // Add external attributes to 302 sticky and editorial links function extLink() { // Sticky 302 links, this fuction opens the link we send to Medium on a new tab and adds a "noopener" rel to them var stickyLinks = document.querySelectorAll('.grid-item.sticky a'); for (var i = 0; i < stickyLinks.length; i++) { /* stickyLinks[i].setAttribute('target', '_blank'); stickyLinks[i].setAttribute('rel', 'noopener'); */ } // Editorial 302 links, same here var editLinks = document.querySelectorAll( '.grid-item.category-editorial a' ); for (var i = 0; i < editLinks.length; i++) { editLinks[i].setAttribute('target', '_blank'); editLinks[i].setAttribute('rel', 'noopener'); } } // Add current year to copyright notices document.getElementById( 'js-current-year' ).textContent = new Date().getFullYear(); // Call functions after page load extLink(); //addAlly(); setTimeout(function() { //addAlly(); //ideally we should only need to run it once ↑ }, 5000); }; function closeCookieDialog (){ document.getElementById("cookie-consent").style.display = "none"; return false; } setTimeout ( function () { closeCookieDialog(); }, 15000); console.log(`%c 🚀🚀🚀 ███ █████ ███████ █████████ ███████████ █████████████ ███████████████ ███████ ███████ ███████ ┌───────────────────────────────────────────────────────────────────┐ │ │ │ Towards AI is looking for contributors! │ │ Join us in creating awesome AI content. │ │ Let's build the future of AI together → │ │ https://towardsai.net/contribute │ │ │ └───────────────────────────────────────────────────────────────────┘ `, `background: ; color: #00adff; font-size: large`); //Remove latest category across site document.querySelectorAll('a[rel="category tag"]').forEach(function(el) { if (el.textContent.trim() === 'Latest') { // Remove the two consecutive spaces (  ) if (el.nextSibling && el.nextSibling.nodeValue.includes('\u00A0\u00A0')) { el.nextSibling.nodeValue = ''; // Remove the spaces } el.style.display = 'none'; // Hide the element } }); // Add cross-domain measurement, anonymize IPs 'use strict'; //var ga = gtag; ga('config', 'G-9D3HKKFV1Q', 'auto', { /*'allowLinker': true,*/ 'anonymize_ip': true/*, 'linker': { 'domains': [ 'medium.com/towards-artificial-intelligence', 'datasets.towardsai.net', 'rss.towardsai.net', 'feed.towardsai.net', 'contribute.towardsai.net', 'members.towardsai.net', 'pub.towardsai.net', 'news.towardsai.net' ] } */ }); ga('send', 'pageview'); -->