2025
Building a GPT from scratch: positional encoding (PE)
Building a GPT from scratch: decoder for text generation
Building a GPT from scratch: token embeddings and training
Building a GPT from scratch: tokenizer and data loader
Understanding Generative Pre-trained Transformers (GPT)
LLMs: addressing limitations and exploring key advancements
Understanding the attention mechanism in transformer networks
A detailed look at transformer networks in language models
Feedback control for a pendulum on a cart
[LinkedIn post] Multiplatform graphics engine publication
Training neural networks on the MNIST dataset