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

Deep Learning from Scratch in Modern C++: Cost Functions
Latest   Machine Learning

Deep Learning from Scratch in Modern C++: Cost Functions

Last Updated on July 17, 2023 by Editorial Team

Author(s): Luiz doleron

Originally published on Towards AI.

Let’s have fun by implementing Cost Functions in pure C++ and Eigen.

In machine learning, we usually model problems as functions. Therefore, most of our work consists of finding ways to approximate functions using well-known models. In this context, Cost Functions play a central role.

This story is a sequel to our previous talk about convolutions. Today, we will introduce the concept of cost functions, show common examples and learn how to code and plot them. As always, from scratch in pure C++ and Eigen.

About this series

In this series, we will learn how to code the must-to-know deep learning algorithms such as convolutions, backpropagation, activation functions, optimizers, deep neural networks, and so on using only plain and modern C++.

This story is: Cost functions in C++

Check other stories:

0 — Fundamentals of deep learning programming in Modern C++

1 — Coding 2D convolutions in C++

3 — Implementing Gradient Descent

4 — Activation Functions

… more to come.

Modeling in machine learning

As artificial intelligence engineers, we usually define every task or problem as a function.

For example, if we are working on a face recognition system, our first step is to define the problem as a function to map an input image to an identifier:

For a medical diagnosis system, we can define a function to map symptoms to diagnostics:

We can write a model to provide an image given a sequence of words:

This is an endless list. Using functions to represent tasks or problems is the streamlined way to implement machine learning systems.

The problem often is: how to know the F() formula?

Approximating Functions

Indeed, defining F(X) using a formula or a sequence of rules is not feasible (one day I shall explain why).

In general, instead of finding or defining the proper function F(X), we try to find an approximation of F(X). Let’s call this approximation by hypothesis function, or simply, H(X).

At first glance, it does not make sense: if we need to find the approximation function H(X), why do we not try to find F(X) directly?

The answer is: we know H(X). Whereas we do not know much about F(X), we know almost everything about H(X): its formula, parameters, etc. The only thing we don’t know about H(X) are its parameter values.

Indeed, the main concern in machine learning is finding ways to determine suitable parameter values for a given problem and data. Let’s see how we can carry it out.

In machine learning terminology, H(X) is said “an approximation of F(X)”. The existence of H(X) is covered by the Universal Approximation Theorem.

Cost Function and The Universal Approximation Theorem

Consider the case where we know the value of the input Xand the respective output Y = F(X) but we do not know the formula of F(X). For example, we know that if the input isX = 1.0 then F(1.0)results inY = 2.0.

4 mapping for X and F(X)

Now, consider that we have a known function H(X) and we are wondering whetherH(X) is a good approximation for F(X). Thus, we calculate T = H(1.0) and find T = 1.9 .

How bad is this value T = 1.9 since we know that the true value is Y = 2.0 when X = 1.0?

The metric to quantify the cost of the difference between Y and T is called by Cost Function.

Note that Y is the expected value and T is the actual value obtained by our guess H(X)

The concept of cost functions is core in machine learning. Let’s introduce the most common cost function as an example.

Mean Squared Error

The most known cost function is the Mean Squared Error:

where Tᵢ is given by the convolution of Xᵢ by kernel k:

We discussed Convolution in the previous story

Note that we have n pairs (Yₙ, Tₙ) each one a combination of the expected value Yᵢ and the actual value Tₙ. For example:

Hence, MSE is evaluated as follows:

We can write our first version of MSE as follows:

auto MSE = [](const std::vector<double> &Y_true, const std::vector<double> &Y_pred) {

if (Y_true.empty()) throw std::invalid_argument("Y_true cannot be empty.");

if (Y_true.size() != Y_pred.size()) throw std::invalid_argument("Y_true and Y_pred sizes do not match.");

auto quadratic = [](const double a, const double b) {
double result = a - b;
return result * result;
};
const int N = Y_true.size();
double acc = std::inner_product(Y_true.begin(), Y_true.end(), Y_pred.begin(), 0.0, std::plus<>(), quadratic);

double result = acc / N;

return result;
};

Now we know how to calculate MSE, let’s see how to use it to approximate functions.

The intuition of using MSE to find the best parameters

Let’s assume that we have a mapping F(X) synthetically generated by:

F(X) = 2*X + N(0, 0.1)

where N(0, 0.1) represents a random value drawn from the normal distribution with mean = 0 and standard deviation = 0.1. We can generate sample data by:

#include <random>

std::default_random_engine dre(time(0));

std::normal_distribution<double> gaussian_dist(0., 0.1);
std::uniform_real_distribution<double> uniform_dist(0., 1.);

std::vector<std::pair<double, double>> sample(90);

std::generate(sample.begin(), sample.end(), [&gaussian_dist, &uniform_dist]() {
double x = uniform_dist(dre);
double noise = gaussian_dist(dre);
double y = 2. * x + noise;
return std::make_pair(x, y);
});

If we plot this sample using any spreadsheet software, we get something like this:

Note that we know the formula of G(X) and F(X). In real life, however, these generator functions are undisclosed secrets of the underlying phenomena. Here, in our example, we only know them because we are generating synthetic data to help us to get a better understanding.

In real life, everything we know is an assumption that the hypothesis function H(X) defined by H(X) = kX might be a good approximation of F(X). Of course, we don’t know what is the value of k yet.

Let’s see how to use MSE to find out a suitable value of k. Indeed, it is as simple as plotting MSE for a range of different k’s:

std::vector<std::pair<double, double>> measures;

double smallest_mse = 1'000'000'000.;
double best_k = -1;
double step = 0.1;

for (double k = 0.; k < 4.1; k += step) {
std::vector<double> ts(sample.size());
std::transform(sample.begin(), sample.end(), ts.begin(), [k](const auto &pair) {
return pair.first * k;
});

double mse = MSE(ys, ts);
if (mse < smallest_mse) {
smallest_mse = mse;
best_k = k;
}

measures.push_back(std::make_pair(k, mse));
}

std::cout << "best k was " << best_k << " for a MSE of " << smallest_mse << "\n";

Very often, this program outputs something like this:

best k was 2.1 for a MSE of 0.00828671

If we plot MSE(k) by k, we can see a very interesting fact:

k from 0 to 4 using steps of 0.1

Note that the value of MSE(k) is minimum in the neighborhood of k = 2. Indeed, 2 is the parameter of the generatrix function G(X) = 2X.

Given the data and using steps of 0.1, the smaller value of MSE(k) is found when k = 2.1. This suggests that H(X) = 2.1X is a good approximation of F(X). In fact, if we plot, F(X), G(X), and H(X), we have:

By the chart above, we can realize that H(X) actually approximates F(X). We can try using smaller steps like 0.01 or 0.001 to find a better approximation, though.

The code can be found on this repository

The Cost Surface

The curve of MSE(k) by k is a one-dimensional example of the Cost Surface.

MSE curve is a 1D surface

What the previous example shows is that we can use the minimum value of the cost surface to find the best fit for the parameter k.

The example describes the most important paradigm in machine learning: functions approximations by cost function minimization.

The previous chart shows a 1-dimensional cost surface, i.e., a cost curve given a single-dimensional k. In 2-D spaces, i.e., when we have two k’s namely k0 and k1, the cost surface looks more like an actual surface:

2D cost surface — source: Wikipedia

Regardless of whether k is 1D, 2D, or even higher-dimensional, the process of finding the best k-th values is the same: finding the smallest value of the cost curve.

The smallest cost value is also known as Global Minima.

In 1D spaces, the process of finding the global minima is relatively easy. However, on high dimensions, scanning all space to find the minima can be computationally costly. In the next story, we will introduce algorithms to perform this search at scale.

Not only k can be high-dimensional. In real problems, very often the outputs are high-dimensional too. Let’s learn how to calculate MSE in cases like this.

MSE on High-Dimensional Outputs

In real-world problems, Y and T are vectors or matrices. Let’s see how to deal with data like this.

If the output is single-dimensional, the previous formula of MSE will work out. But if the output is multi-dimensional, we need to change the formula a little bit. For example:

In this case, instead of scalar values, Yₙ and T are matrices of size (2,3). Before applying MSE to this data, we need to change the formula as follows:

In this formula, N is the number of pairs, R is the number of rows, and C is the number of columns in each pair. As usual, we can implement this version of MSE using lambdas:

#include <numeric>
#include <iostream>

#include <Eigen/Core>

using Eigen::MatrixXd;

int main()
{

auto MSE = [](const std::vector<MatrixXd> &Y_true, const std::vector<MatrixXd> &Y_pred)
{

if (Y_true.empty()) throw std::invalid_argument("Y_true cannot be empty.");

if (Y_true.size() != Y_pred.size()) throw std::invalid_argument("Y_true and Y_pred sizes do not match.");

const int N = Y_true.size();
const int R = Y_true[0].rows();
const int C = Y_true[0].cols();

auto quadratic = [](const MatrixXd a, const MatrixXd b)
{
MatrixXd result = a - b;
return result.cwiseProduct(result).sum();
};

double acc = std::inner_product(Y_true.begin(), Y_true.end(), Y_pred.begin(), 0.0, std::plus<>(), quadratic);

double result = acc / (N * R * C);

return result;
};

std::vector<MatrixXd> A(4, MatrixXd::Zero(2, 3));
A[0] << 1., 2., 1., -3., 0, 2.;
A[1] << 5., -1., 3., 1., 0.5, -1.5;
A[2] << -2., -2., 1., 1., -1., 1.;
A[3] << -2., 0., 1., -1., -1., 3.;

std::vector<MatrixXd> B(4, MatrixXd::Zero(2, 3));
B[0] << 0.5, 2., 1., 1., 1., 2.;
B[1] << 4., -2., 2.5, 0.5, 1.5, -2.;
B[2] << -2.5, -2.8, 0., 1.5, -1.2, 1.8;
B[3] << -3., 1., -1., -1., -1., 3.5;

std::cout << "MSE: " << MSE(A, B) << "\n";

return 0;
}

It is noteworthy that, regardless k or Y are or are not multi-dimensional, MSE is always a scalar value.

Other Cost Functions

In addition to MSE, other cost functions are also regularly found in deep learning models. The most commons are categorial cross-entropy, log cosh, and cosine similarity.

We will cover these functions in forthcoming stories, in particular when we cover classification and non-linear inference.

Conclusion and Next Steps

Cost Functions are one of the most important topics in machine learning. In this story, we learned how to code MSE, the most used cost function, and how to use it to fit single-dimensional problems. We also learned why cost functions are so important to find function approximations.

In the next story, we will learn how to use cost functions to train convolution kernels from data. We will introduce the base algorithm to fit kernels and discuss the implementation of training mechanics such as epochs, stop conditions, and hyperparameters.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments 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.

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'); -->