Pinned Repositories
ARC
The Abstraction and Reasoning Corpus
Auto-GPT
An experimental open-source attempt to make GPT-4 fully autonomous.
bsuite
bsuite is a collection of carefully-designed experiments that investigate core capabilities of a reinforcement learning (RL) agent
COMP0090
UCL Module: Introduction to Deep Learning
conala-baseline
Baseline for the Conala: Code/Natural Language Challenge
csml-reading-group
UCL ARC computational statistics and machine learning reading group
deep_learning_and_the_game_of_go
Code and other material for the book "Deep Learning and the Game of Go"
dm-haiku
JAX-based neural network library
ENGS101PWebsite
jax
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
TerryW9UCL's Repositories
TerryW9UCL/csml-reading-group
UCL ARC computational statistics and machine learning reading group
TerryW9UCL/dm-haiku
JAX-based neural network library
TerryW9UCL/jax
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
TerryW9UCL/ARC
The Abstraction and Reasoning Corpus
TerryW9UCL/Auto-GPT
An experimental open-source attempt to make GPT-4 fully autonomous.
TerryW9UCL/bsuite
bsuite is a collection of carefully-designed experiments that investigate core capabilities of a reinforcement learning (RL) agent
TerryW9UCL/COMP0090
UCL Module: Introduction to Deep Learning
TerryW9UCL/conala-baseline
Baseline for the Conala: Code/Natural Language Challenge
TerryW9UCL/deep_learning_and_the_game_of_go
Code and other material for the book "Deep Learning and the Game of Go"
TerryW9UCL/fp_guides_wiki
All study notes and guides for the futureproof curriculum
TerryW9UCL/gpt-3
GPT-3: Language Models are Few-Shot Learners
TerryW9UCL/intro_to_deep_rl
TerryW9UCL/jaxsim
A scalable physics engine implemented with JAX. With JIT batteries :battery:
TerryW9UCL/jpacman-framework-2
TerryW9UCL/jpacman-framework-3
COMP0104 - Lab08a
TerryW9UCL/jwave
A JAX-based research framework for differentiable and parallelizable acoustic simulations, on CPU, GPUs and TPUs
TerryW9UCL/lczero.org
A website (will be lczero.org)
TerryW9UCL/mujoco_menagerie
A collection of high-quality models for the MuJoCo physics engine, curated by DeepMind.
TerryW9UCL/open_spiel
OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.
TerryW9UCL/openvino
OpenVINO™ Toolkit repository
TerryW9UCL/pachi
A fairly strong Go/Baduk/Weiqi playing program
TerryW9UCL/pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
TerryW9UCL/scikit-learn
scikit-learn: machine learning in Python
TerryW9UCL/SCOD
Code accompanying "Sketching Curvature for Efficient Out-of-Distribution Detection for Deep Neural Networks"
TerryW9UCL/stable_diffusion_playground
Playing around with stable diffusion. Generated images are reproducible because I save the metadata and latent information. You can generate and then later interpolate between the images of your choice.
TerryW9UCL/Stockfish
UCI chess engine
TerryW9UCL/tensorflow
An Open Source Machine Learning Framework for Everyone
TerryW9UCL/Terry_Weiqi-Go_Baduk_Python_26_November_2023_Sunday
Terry_Weiqi-Go_Baduk_Python_26_November_2023_Sunday
TerryW9UCL/test
TerryW9UCL/trfl
TensorFlow Reinforcement Learning