Reinforcement Learning with continuous state spaces and gradient descent techniques — Since Part 1 of this series, we have framed Reinforcement Learning as a Markov Decision Process environment with discrete states and actions with their corresponding state-action values Q(s,a) stored in a tabular manner. This means that you can imagine a 2-dimensional table, with a row index presented by states and…

Introducing the Temporal Difference family of iterative techniques to solve the Markov Decision Process — In the previous article — Part 2 — we discovered a few solution algorithms to solve the Markov Decision Process (MDP), namely the Dynamic Programming method and the Monte Carlo method. The Dynamic Programming approach can be easily applied when we know the entire environmental dynamics of the MDP, such…

Introducing two simple iterative techniques to solve the Markov Decision Process — In the previous article — Part 1 — we have formulated the Markov Decision Process (MDP) as a paradigm to solve any Reinforcement Learning (RL) problem. However, the overarching framework discussed did not mention a systematic solution to the MDP. We have ruled out using linear techniques — like matrix…

Introducing the backbone of Reinforcement Learning — The Markov Decision Process — In most of my previous articles, I have mostly discussed Supervised Learning, with some sprinkling of elements of Unsupervised Learning. However, in this and the next few articles, I will attempt to attack the problem of Reinforcement Learning and give you, the reader, a clear and intuitive idea of how…

Designing customized GANs for image-to-image translation to augment glasses onto faces — Quick Note: I will be starting the challenging OMSCS Masters program very soon. Hence I would be writing less frequently. However, I hope to return every semester break to write about the subject that I have learned in the preceding semester. For instance, you can expect me to write about…

Theory & Code-along: Triplet loss with cosine distance for Siamese Networks on CIFAR-10 dataset — What if we could encode every object image (human faces, etc) into a template — a vector of numbers? Thereafter, we could objectively determine the similarity between objects by numerically comparing — finding the distances — between their templates. …

Part 1 — Cognitive Revolution — of the complete summary of Sapiens: A Brief History of Humankind — Once in a few years, a revolutionary and eye-opening book is published that questions our assumptions and reshapes our understanding of the world around us. Sapiens: A Brief History of Humankind, written by Yuval Noah Harari in 2014, is an exemplar of such literature. …

A comprehensive guide to data generation strategy for data-centric Machine Learning projects — In the world of deep learning, complex models are data-hungry — in both quality and quantity — to perform well on inference at test time. However, in real-world Artificial Intelligence projects by commercial companies, Machine Learning Engineers seldom have the luxury of readily available training data. …

A complete discussion on the nature of happiness, and the strategies to achieve well-being — Hundreds of thousands of humans are born each day into a world already occupied by billions. As with everyone who came before them, they will go through the motions of life — growing up, forging their future, and retiring in old age. Yet, despite the multitude of beings, we can…