John Machado

Build-a-Large-Language-Model-from-Scratch. Building a GPT-like LLM from scratch with PyTorch.

Neural-Networks-from-Scratch-in-Python. Building neural networks from scratch only with Python and NumPy. This covers coding neurons, layering them, using activation functions, calculating loss, backpropagation, and optimizing parameters.

RPA-Challenge. RPA (Robotic Process Automation). Automating the extraction of user data from an Excel file and inputting it into a website with dynamically changing form field positions.

ReAct-Agent-from-Scratch. ReAct (Reasoning and Acting) agent built from scratch in Python. No libraries, no abstractions, simple and straight to the point.

Cloud-Python-to-Cpp. Python backend built utilizing several Google Cloud Platform services. In addition, C++ connectivity, a robust cloud authentication system, Cloud Build CI/CD pipelines, process automation, and more.

AirQNet. AirQNet (Air Quality Network) is a 10,886 parameter neural network built with PyTorch for air quality classification.

CS102-Data-Structures-and-Algorithms-Codecademy. Python

Coding-Dojo-Basic-13-Javascript. The "Basic 13" Algorithms from Coding Dojo

CS104-Computer-Architecture. Python implementation of a 32-bit processor with its own ISA (Instruction Set Architecture)

Practical-Machine-Learning-with-Python. An all-encompassing exploration of machine learning, including the theoretical aspects, real-world applications, and the intricate details of supervised and unsupervised algorithms.

Serverless-Python. Python / FastAPI application running on Google Cloud Run

High-Temp. A 1 - 2 player computer terminal game which uses live temperature data of cities using the API from weatherapi.com. Higher the temperature of your city and you win!

ReAct-Agent-plus-TextWorld. ReAct (Reasoning and Acting) agent built from scratch in Python, adapted to interact with Microsoft’s TextWorld environments.