Archive - Vizuara’s Substack

The three horsemen of Classical Reinforcement Learning

All about Dynamic Programming, Monte-Carlo and Temporal Difference Methods

Aug 8 •

Hands-on RL Bootcamp Lecture 1

A practical and easy-to-follow program from Q-learning and DQNs to RLHF and GRPO!

Aug 1 •

July 2025

Multi-modal representation learning : A deepdive and comparison of CLIP, SIGLIP and BLIP architectures

This article discusses in detail about refined parametric methods like CLIP, BLIP and SIGLIP, which help us in designing of a architecture capable of…

Jul 28 •

A Primer on Self-supervised Learning

Learn without labels, think beyond tasks. Self-Supervised Learning is how machines teach themselves, from contrast to clustering, from pixels to…

Jul 14 •

Decoding Naive Bayes: From Word Counts to Smart Predictions

Uncover the simple yet powerful math of probability that powers spam filters and text classifiers. Discover how Bayes' Theorem and a "naive" assumption…

Jul 10 •

Decoding the Transformer: From Sequential Chains to Parallel Webs of Attention

Unravel the architecture that dethroned RNNs. Discover how Self-Attention allows models to look at all words at once, enabling parallel processing and a…

Jul 8 •

Decoding Multi-Head Latent Attention (Part 2): Solving the RoPE Paradox

In Part 1, we solved the memory wall with latent compression. Now, discover how standard RoPE breaks this efficiency and why DeepSeek's "Decoupled RoPE…

Jul 7 •

Decoding Multi-Head Latent Attention (Part 1): The KV Cache Memory Bottleneck, Solved.

Discover why the KV Cache is the biggest bottleneck in LLM inference, how MQA and GQA tried to fix it, and how DeepSeek's Latent Attention masterfully…

Jul 6 •

Welcome to the Era of Experience!

Why Reinforcement Learning will dominate the next phase of AI intelligence.

Jul 5 •

Vizuara AI Agents Bootcamp Day 10

n8n and AI Automation

Jul 4 •

Vizuara AI Agents Bootcamp Day 9

CrewAI: A simple yet powerful platform for building multi-agent frameworks

Jul 4 •

Decoding Convolutional Neural Networks: From Pixels to Patterns

Discover how CNNs mimic the human eye with sliding filters, learn to see features instead of just pixels, and unlock the power of image classification.

Jul 3 •

#nojs-banner { position: fixed; bottom: 0; left: 0; padding: 16px 16px 16px 32px; width: 100%; box-sizing: border-box; background: red; color: white; font-family: -apple-system, "Segoe UI", Roboto, Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 13px; line-height: 13px; } #nojs-banner a { color: inherit; text-decoration: underline; } This site requires JavaScript to run correctly. Please turn on JavaScript or unblock scripts