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

Unveiling and Addressing Bias in Natural Language Processing
Latest   Machine Learning

Unveiling and Addressing Bias in Natural Language Processing

Last Updated on July 17, 2023 by Editorial Team

Author(s): Yunzhe Wang

Originally published on Towards AI.

Understanding and mitigating bias in word embeddings and their implications on AI fairness

image by Midjourney

The rapid growth of artificial intelligence (AI) and natural language processing (NLP) in recent years has transformed various industries, from healthcare to finance. As AI systems continue to weave themselves into the fabric of our daily lives, ensuring that these systems are fair, transparent, and unbiased becomes increasingly important. Bias in AI and NLP can emerge in different ways — from the data collection and training process to the algorithms' design, and can inadvertently perpetuate or even amplify existing societal biases and stereotypes.

Hungarian is a gender-neutral language with no gendered pronouns, so Google Translate automatically chooses the gender for you. Image source @DoraVargha from Twitter

Within NLP, biases can be encoded in word embeddings, which are mathematical representations of words that capture their meaning and semantic relationships. When biases find their way into word embeddings, they can unintentionally affect the AI systems that utilize them, leading to unfair or discriminatory outcomes. For example, gender bias present in word embeddings can reinforce gender stereotypes and contribute to unequal treatment of different genders in AI applications, such as recommendation systems, translation services, and resume scoring.

In this post, we will delve into the various types of biases found in word embeddings, examine the methodologies used to detect them and explore the techniques that can help mitigate or eliminate them.

Identifying Bias in Word Embeddings

The first step in addressing bias in NLP systems is to identify and measure the presence of biases in word embeddings. In the field of psychology, the Implicit Association Test (IAT) has been widely used to measure implicit biases in humans by examining the latency in reaction times to presented pairs of words. For example, the IAT might measure the response times when associating “man” with “math” and “woman” with “art.” The differences in response times can reveal underlying biases in how we perceive and associate these concepts.

In a similar vein, we can apply the concept of the IAT to word embeddings. Word embeddings, such as Word2Vec and GloVe, are trained on large text corpora and encode semantic relationships between words as vectors. These vectors can then be used to perform analogy tests that reveal potential biases in the embeddings. For example, if the analogy “man is to computer programmer as woman is to homemaker” holds for a given word embedding, the model encodes a gender stereotype.

Word2Vec and GloVe word embeddings.

Researchers have developed the Word Embedding Association Test (WEAT) to detect biases in word embeddings systematically. WEAT compares two sets of target words (e.g., male and female names) and two sets of attribute words (e.g., career and family-related words) and tests the null hypothesis that there is no difference in the semantic similarity between the target sets and attribute sets. By permuting all combinations of target sets and attribute sets, WEAT calculates a test statistic that quantifies the degree of association between target and attribute word sets. If there is no bias present, the difference in association scores should not be significant. On the other hand, if a bias is detected, we can identify which pairs of input and target words contribute to the observed bias.

WEAT has successfully identified biases in various dimensions, such as gender, race, and age, in popular word embeddings like Word2Vec and GloVe. The results of these tests have shed light on how biases present in the training data can inadvertently become embedded in the word vectors, leading to the potential reinforcement of stereotypes and discriminatory behavior in AI systems built on top of these word embeddings.

Gender Bias in Word Embeddings

A particularly pervasive form of bias in word embeddings is gender bias, which can have significant implications for AI fairness and the perpetuation of stereotypes. Using the Word Embedding Association Test (WEAT), researchers have uncovered gender biases in popular word embeddings, such as Word2Vec and GloVe, revealing that women are more associated with family-related words, while men are more associated with career-related words.

These findings highlight how cultural history and societal norms can become embedded in the usage and associations of words in a language. As word embeddings are trained on large text corpora, essentially reflections of human language and cultural history, it is unsurprising that they may inadvertently capture and perpetuate existing biases.

One notable implication of these findings is that AI systems built on biased word embeddings can inadvertently reinforce stereotypes and contribute to biased behavior. For example, a machine translation system trained on biased embeddings might translate a sentence about a doctor to use a male pronoun in one language and a female pronoun in another, thus perpetuating gender stereotypes associated with certain professions.

Detecting Bias in Sentence Embeddings

While word embeddings have shown evidence of bias, examining whether these biases are also present in sentence embeddings is crucial. Sentence embeddings are capable of capturing the context and semantics of an entire sentence. Researchers have developed the Sentence Encoder Association Test (SEAT) to detect potential bias in these embeddings.

SEAT is an extension of the WEAT and is applied to simple sentence templates where the target word is inserted. For example, given the template “This is <word>”, it could compare embeddings of sentences like “This is Adam” and “This is Jasmine” to measure potential gender bias. Researchers can identify any inherent biases within the model by analyzing these sentence embeddings.

In addition to examining gender bias, SEAT has been employed to uncover other types of biases. One such bias is the “angry black woman” stereotype, where black women are portrayed as loud, angry, and imposing. Another example is the “double bind” women face in professional settings. This bias states that if women succeed in male-dominated professions, they are often perceived as less likable and more hostile than their male counterparts who perform at a similar level.

It is essential to note that the results of SEAT may not generalize beyond the specific words and sentences used in the dataset. Additionally, cosine similarity, a common metric used to measure representational similarity in word embeddings, may not be suitable for newer models like BERT. Despite these limitations, SEAT provides valuable insights into potential biases present in sentence embeddings and helps us understand how these biases may impact the performance and fairness of NLP systems.

Debiasing Techniques and Their Limitations

In our pursuit of creating fairer NLP systems, various debiasing techniques have emerged to address the biases present in word embeddings. In this section, we will discuss two primary methods for debiasing word embeddings and explore their limitations.

Method 1: Post-processing Debiasing

One approach to debiasing is to process the word embeddings after they have been trained. By defining gender bias as the projection of a word on the “gender” direction, we can zero out the gender component for each word. This method aims to eliminate gender bias by effectively removing gender-related information from the embeddings. However, this technique has its limitations. As we will see later in this section, biases often remain even after post-processing.

Method 2: Modifying the Loss Function During Training

Another approach involves training debiased word embeddings from scratch by modifying the loss function of the training algorithm, such as GloVe. In this method, we attempt to concentrate gender information in the last coordinate of the word embeddings by splitting the embeddings into gendered and non-gendered components. Neutral gender words are made orthogonal to the gendered components. When using these word embeddings, we can ignore the last coordinate, effectively removing gender information. However, this method has also been shown to be insufficient in completely eradicating bias.

Limitations of Debiasing Techniques: Although these debiasing methods show some promise, they have several limitations that hinder their effectiveness.

  1. Bias by Neighbors: A word that is biased toward a gender may have neighboring words that are also biased toward that gender. Simply debiasing the relationship between a word and gender doesn’t eliminate the bias from its neighboring words. For example, if “nurse” is associated with females, its neighboring words like “receptionist” or “caregiver” might also be associated with females. As a result, even after debiasing the direction from the word to the gender, the bias may still persist due to the relationships between neighboring words and gender.
  2. Incomplete Bias Removal: Studies have shown that with both debiasing methods, some bias still remains. Most word pairs maintain their previous similarity, which indicates that the biases have not been entirely removed. To further investigate this issue, researchers have clustered the most biased words in the vocabulary before and after debiasing. The analysis of these clusters revealed that there was still a strong association with gender even after the debiasing process.
  3. Classifier Performance: Another way to evaluate the efficacy of debiasing techniques is to train a classifier to predict the gender of a word based on its embeddings. Using the 5,000 most biased gendered words, researchers trained a support vector machine (SVM) classifier on 1,000 random samples and predicted the gender for the remaining 4,000 words. The results showed that the prediction accuracy dropped only marginally with both debiasing methods, suggesting that the debiased embeddings still carry significant gender information.
Clustering for HARD-DEBIASED (post-processing) embedding, before (left-hand-side) and after (right-hand-side) debiasing, a clear separation can still be seen, though explicit effort in debiasing. Figure 1 (a). Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove Them Source: (Gonen and Goldberg 2019)

These limitations highlight the challenges faced in addressing biases in NLP systems. Despite the progress made in developing debiasing techniques, they have not yet proven to be completely effective in eliminating biases from word embeddings. It is essential for researchers and AI practitioners to continue exploring new methods and refining existing techniques to address bias in NLP better and build fairer AI systems.

Towards Fairer NLP Systems

As we have explored the presence of bias in word and sentence embeddings, it becomes clear that addressing these biases is crucial in developing fair and unbiased AI systems. To this end, we must consider various strategies to mitigate bias and promote ethical AI development.

One of the primary approaches to reducing bias is incorporating diverse training data. By including a wide range of text sources that represent different genders, races, cultures, and perspectives, we can create a more balanced foundation for AI models to learn from. This can lead to more representative word and sentence embeddings that better reflect the true diversity of human language.

In addition to diversifying training data, ethical AI frameworks can guide developers in designing and evaluating their systems. By adhering to guidelines and best practices that prioritize fairness, accountability, and transparency, AI practitioners can create more robust and unbiased models. Collaborating with ethicists and social scientists can provide valuable insights into the ethical implications of AI systems and help identify potential pitfalls in their development.

Interdisciplinary collaboration can also play a significant role in mitigating biases. By combining the expertise of linguists, computer scientists, psychologists, and sociologists, we can develop a more comprehensive understanding of the cultural and societal factors that contribute to bias in NLP systems. This collaborative approach can lead to novel debiasing techniques and more effective measurements of bias in AI models.

In conclusion, addressing bias in natural language processing systems is paramount for ensuring fairness and ethical AI applications. As we have seen, biases in word embeddings and sentence encodings can reinforce existing stereotypes and perpetuate harmful beliefs. While researchers have made progress in detecting and mitigating these biases, existing debiasing techniques are not yet perfect and may still leave some residual bias in the system.

As AI practitioners, it is our responsibility to be aware of our work's biases and seek ways to minimize their impact actively. By incorporating diverse training data, adopting ethical AI frameworks, and fostering interdisciplinary collaboration, we can move closer to creating fair and unbiased NLP systems. Ultimately, our efforts to tackle bias in AI will result in more accurate and useful technologies and contribute to a more equitable and just society.

References

[1] Caliskan, Aylin, Joanna J. Bryson, and Arvind Narayanan. Semantics derived automatically from language corpora contain human-like biases. (2017) Science 356.6334: 183–186.

[2] Bolukbasi, Tolga, et al. Man is to computer programmer as woman is to homemaker? debiasing word embeddings. (2016) Advances in neural information processing systems 29.

[3] May, Chandler, et al. On measuring social biases in sentence encoders. (2019) arXiv preprint arXiv:1903.10561.

[4] Gonen, Hila, and Yoav Goldberg. (2019) Lipstick on a pig: Debiasing methods cover up systematic gender biases in word embeddings but do not remove them. arXiv preprint arXiv:1903.03862.

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'); -->