stewy33 Goto Github PK

ar-project

assembling-jigsaw-puzzles-efficiently

Reimplementing the 2016 paper "Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles".

chatgpt-system-prompts

This repository contains a collection of the best system prompts for ChatGPT, a conversational AI model developed by OpenAI. Star this repository to help us reach 5,000 stars!

clevr-dataset-gen

A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning

discourse

Discourse - a study app based on natural language interactions.

easytex

A browser-based math editor focused on readability.

elkridge-food-pantry

For distributed development of

gpustat-web

👓 A web interface of gpustat: monitor GPU clusters at a look

haskell-raytracer

A raytracer written in Haskell.

haskell-skiplist

A pure implementation of a skiplist in Haskell.

imitation

Clean PyTorch implementations of imitation and reward learning algorithms

lamp-project

learning-to-optimize

An implementation of the 2016 meta-learning paper "Learning to Optimize" from the BAIR lab at Berkeley.

magicmirror

Our personal version of MagicMirror² for our apartment in Uni One.

making-rational-protein-design-artifically-intelligent

Our final project for Deep Learning in Discrete Optimization taught by Bill Cook. We developed an ML-based branching rule for solving Protein Design problems in Weighted Constraint Satisfaction form.

merchant

A package manager for the Mercury logic programming language.

mercury-json

A Mercury JSON library.

mercury-vim

Personal fork of a Vim plugin for the Mercury language.

motion-planning-in-carla

My final project solution from Coursera's Motion Planning for Self-Driving Cars.

nn-functional-mapping-visualization

Visualization tool for neural networks that transforms high dimensional functional relationships between nodes into spatial ones.

phaedrus-gpt

A Raspberry Pi voice assistant powered by OpenAI Whisper, Chat-GPT, and Google/ElevenLabs TTS.

pong-with-policy-gradients

Code for an intro to RL workshop. You'll be training a simple agent to play pong using policy gradients. Adapted from http://karpathy.github.io/2016/05/31/rl/

safe-grid-gym

A gym interface for AI safety gridworlds created in pycolab.

safety-gym

Tools for accelerating safe exploration research.

sail-paper-code

sail-study

An orthopedic education tool based on natural language interactions.

seals

Benchmark environments for reward modelling and imitation learning algorithms.

stanford-cs224n-assignments

Completed assignments as I work through Stanford's CS224n: Natural Language Processing with Deep Learning

stanford-cs234-assignments

Completed assignments from Stanford's CS234: Reinforcement Learning course.

stewy33.github.io

My personal website :)