Piyush Thakur

The report explains how to build a fast and accurate social distance detector to run on-device inference using real-time video feed

In this article, we will learn about Retrieval Augmented Generation (RAG) and how it helps pre-trained LLM models to generate more specific, diverse and factual responses.

In this article, we will explore Q-learning: a model-free, off-policy and value-based reinforcement learning algorithm.

In this article, we will show practical implementation of Q-learning using gymnasium's cliff walking environment.