Archive - Curiosity-driven AI/ML Research Engineering

Bias trick in neural networks

Turning two tensors (weights and biases) into one (weights with biases) for simpler computation in neural networks

May 21 •

Jędrzej Maczan

April 2024

Let's build Text-to-ML: an AutoML library that operates natural language

Like a combination of HuggingGPT, LangChain and Python type inference

Apr 4 •

Jędrzej Maczan

AlexNet from scratch in PyTorch Lightning

Convolutional Neural Network architecture explained

Apr 2 •

Jędrzej Maczan

February 2024

So you want to code a convolution in Python - a bite-sized image processing with kernel

Implementing 🌸 tinyconv with Kirby for fun and learning

Feb 16 •

Jędrzej Maczan

#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