← Back to Portfolio

My AI Engineering Journal

Exploring deep learning, AI systems, and building from scratch

7 Total Articles
7 Showing

From Scratch Implementation of ResShift Paper for Image Super-Resolution

Coming Soon · Diffusion Models · Computer Vision

A deep dive into implementing the ResShift paper from scratch for efficient diffusion-based image super-resolution. Learn about U-Net architecture with Swin Transformer blocks, residual shifting mechanisms, and building state-of-the-art image enhancement models.

Diffusion Models Computer Vision Deep Learning From Scratch

From Scratch Implementation of RNN, LSTM and BiLSTM: What I Learned

Coming Soon · Neural Networks · Sequence Modeling

Exploring the inner workings of Recurrent Neural Networks by implementing RNN, LSTM, and Bidirectional LSTM from scratch. This post covers forward propagation, backpropagation through time (BPTT), and the key insights gained from building these architectures from the ground up.

RNN LSTM Neural Networks From Scratch

ML Training Optimization: FLOPs, Profiling, and Learning Strategies

Oct 20th, 2025 · 12 min read

A comprehensive guide to optimizing machine learning training, covering computational constraints, performance profiling, and learning strategies that can save significant costs and time.

Machine Learning Optimization Training

From Quantization to Inference: Beginners Guide for Practical Finetuning

Published in Towards AI · Apr 25th, 2025

A beginner-friendly guide that bridges the gap between quantization and inference, providing practical insights into fine-tuning techniques.

Quantization Fine-tuning Deep Learning

Building GPT from First Principles: Code and Intuition

Published in Towards AI · Apr 30th, 2025

An intuitive and code-driven exploration of building GPT models from scratch, unraveling the principles behind their architecture.

GPT AI Models Deep Learning

Understanding Quantization in Deep Learning

Mar 13th, 2025 · 15 min read

A comprehensive guide to memory optimization in deep learning, focusing on quantization techniques and their practical implementation in modern neural networks.

Deep Learning Optimization Neural Networks

A Guide to Fine-tuning Methods in LLMs (Part 1)

Mar 17th, 2025 · 20 min read

A deep dive into modern fine-tuning techniques for Large Language Models, exploring methods like LoRA, QLoRA, and their practical implementations.

LLMs Fine-tuning Deep Learning