I want to talk about technical approaches to mitigating algorithmic bias.It’s 2019, and the majority of the ML community is finally publicly acknowledging the prevalence and consequences of bias in ML models. For years, dozens of reports by organizations such as ProPublica and the New York Times have been exposing the scale of algorithmic discrimination in criminal risk … [Read more...] about Algorithmic Solutions to Algorithmic Bias: A Technical Guide
Technical Guide
OpenAI’s GPT-2: Results, Hype, and Controversies
The nonprofit AI research company, OpenAI, recently released a new language model, called GPT-2, which is capable of generating realistic texts in a wide range of styles. In fact, the company stated that the model is so good at automatic text generation that it can be used for nefarious purposes; therefore, it did not publicize the trained model.The dangerous-to-release … [Read more...] about OpenAI’s GPT-2: Results, Hype, and Controversies
10 Best A/B and Multivariate Testing Tools for Conversion Rate Optimization
A website interface or an app plays an important role in any marketing strategy. A good-looking landing page that engages and communicates the right message can sell almost anything. But what if it doesn’t? To answer this question, businesses have been testing and verifying their design assumptions for years.There are a great number of UX testing types, but the most popular … [Read more...] about 10 Best A/B and Multivariate Testing Tools for Conversion Rate Optimization
The Multi-Armed Bandit Problem and Its Solutions
The multi-armed bandit problem is a classic example to demonstrate the exploration versus exploitation dilemma. This post introduces the bandit problem and how to solve it using different exploration strategies.Exploitation vs ExplorationWhat is Multi-Armed Bandit?DefinitionBandit Strategiesε-Greedy AlgorithmUpper Confidence BoundsHoeffding’s InequalityUCB1Bayesian … [Read more...] about The Multi-Armed Bandit Problem and Its Solutions
Top 8 Trends From ICLR 2019
1. InclusivityThe organizers pressed the importance of inclusivity in AI by making sure that the first two main talks, the Sasha Rush’s opening remarks and Cynthia Dwork’s invited talk, were about fairness and equality. Some of the worrisome statistics include:Only 8.6% of presenters and 15% of participants are women.2/3rd of all the LGBTQ+ researchers aren’t out … [Read more...] about Top 8 Trends From ICLR 2019
The Most Important Data Science Tool for Market and Customer Segmentation
Market and customer segmentation are some of the most important tasks in any company. The segmentation done will influence marketing and sales decisions, and potentially the survival of a company.Surprisingly, despite the advance in machine learning, few marketers are using such technology to augment their all-important market and customer segmentation efforts.In this … [Read more...] about The Most Important Data Science Tool for Market and Customer Segmentation
Intuitively Understanding Convolutions for Deep Learning
The advent of powerful and versatile deep learning frameworks in recent years has made it possible to implement convolution layers into a deep learning model an extremely simple task, often achievable in a single line of code.However, understanding convolutions, especially for the first time can often feel a bit unnerving, with terms like kernels, filters, channels and so … [Read more...] about Intuitively Understanding Convolutions for Deep Learning
An In-Depth Guide To Generative Adversarial Networks (GANs)
Generative Adversarial Networks are a powerful class of neural networks with remarkable applications. They essentially consist of a system of two neural networks — the Generator and the Discriminator — dueling each other.Given a set of target samples, the Generator tries to produce samples that … [Read more...] about An In-Depth Guide To Generative Adversarial Networks (GANs)
A Simple Guide to Semantic Segmentation
Semantic Segmentation is the process of assigning a label to every pixel in the image. This is in stark contrast to classification, where a single label is assigned to the entire picture. Semantic segmentation treats multiple objects of the same class as a single entity. On the other hand, instance segmentation treats multiple objects of the same class as distinct individual … [Read more...] about A Simple Guide to Semantic Segmentation
A Beginner-Friendly Introduction to Reinforcement Learning
For those of you who are completely new to Reinforcement Learning, we've searched through beginner-friendly content across the internet and chose to feature this introductory video which we think presents one of the best technical but still understandable introductions to the field.In this very accessible video, Xander Steenbrugge talks about:the explosion of the … [Read more...] about A Beginner-Friendly Introduction to Reinforcement Learning