ConnorWatts

AI-Scientist

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬

algo-trader

Trading bot with support for realtime trading, backtesting, custom strategies and much more.

autotagger

Tagger for recipes

bayeSDE

Code for "Infinitely Deep Bayesian Neural Networks with Stochastic Differential Equations"

ConnorWatts.github.io

Personal research website

mtl-gan

Multi-Task Learning framework for Image Generative Adversarial Network

Multi-Task-Genre-Classification

Multi-task learning models built for song genre classification made as a group project for the Natural Language Processing course at UCL. Here we consider both BERT and CNN based architectures.

port-rl

Reinforcement Learning based Portfolio Manager. Here the agent allocate portions of a fund to different financial products with the goal of maximising returns. Currently supports DDPG and PPO.

rubix

Deep Reinforcement Learning based Rubik’s Cube solver written in JAX, Haiku and RLax. Developed a custom environment supporting cubes of variable size. Currently developing support for DQN, QR-DQN and PPO.

time-gebm

Two Generalized Energy Based Models for time-series generation. Thesis for MSc Computational Statistics and Machine Learning program at UCL.

ConnorWatts/mtl-gan

Multi-Task Learning framework for Image Generative Adversarial Network

ConnorWatts/port-rl

Reinforcement Learning based Portfolio Manager. Here the agent allocate portions of a fund to different financial products with the goal of maximising returns. Currently supports DDPG and PPO.

ConnorWatts/time-gebm

Two Generalized Energy Based Models for time-series generation. Thesis for MSc Computational Statistics and Machine Learning program at UCL.

ConnorWatts/rubix

Deep Reinforcement Learning based Rubik’s Cube solver written in JAX, Haiku and RLax. Developed a custom environment supporting cubes of variable size. Currently developing support for DQN, QR-DQN and PPO.

ConnorWatts/AI-Scientist

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬

ConnorWatts/algo-trader

Trading bot with support for realtime trading, backtesting, custom strategies and much more.

ConnorWatts/autotagger

Tagger for recipes

ConnorWatts/bayeSDE

Code for "Infinitely Deep Bayesian Neural Networks with Stochastic Differential Equations"

ConnorWatts/ConnorWatts.github.io

Personal research website

ConnorWatts/deploying-machine-learning-models

Code for the online course "Deployment of Machine Learning Models"

ConnorWatts/enn

ConnorWatts/Multi-Task-Genre-Classification

Multi-task learning models built for song genre classification made as a group project for the Natural Language Processing course at UCL. Here we consider both BERT and CNN based architectures.

ConnorWatts/Multi-Task-Learning-for-Image-Seg

A multi-task learning model built for image segmentation made as a group project for the Deep Learning course at UCL

ConnorWatts/GeneralizedEBM

ConnorWatts/gym

Fully differentiable RL environments, written in Ivy.

ConnorWatts/jraph-cut

Reinforcement Learning (RL) environments for a range of graph problems. Written in Jraph.

ConnorWatts/liquid-s4

Liquid Structural State-Space Models

ConnorWatts/MLOps

MLOps examples

ConnorWatts/part_stoch_inf_deep

Partially Stochastic but Infinitely Deep Neural Networks

ConnorWatts/Stable-Neural-SDEs

ConnorWatts/torchsde

Differentiable SDE solvers with GPU support and efficient sensitivity analysis.