j-towns

bits-back

jax

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

autograd

Efficiently computes derivatives of numpy code.

ans-notes

Tutorial paper and code for rANS

craystack

Compression tools for machine learning researchers

fastar

flipper

Reversible programming in Agda

iprofiler

Interactive code profiling widget for IPython + Jupyter Notebook

vdvae-jax

Very deep VAEs in JAX/Flax

pymanopt

Python toolbox for optimization on Riemannian manifolds with support for automatic differentiation

j-towns/craystack

Compression tools for machine learning researchers

j-towns/vdvae-jax

Very deep VAEs in JAX/Flax

j-towns/iprofiler

Interactive code profiling widget for IPython + Jupyter Notebook

j-towns/fastar

j-towns/flipper

Reversible programming in Agda

j-towns/ans-notes

Tutorial paper and code for rANS

j-towns/ssm-code

Code for the paper "Lossless compression with state space models using bits back coding" - https://arxiv.org/abs/2103.10150

j-towns/crayjax

JAX implementation of vectorized rANS.

j-towns/flax

Flax is a neural network library for JAX that is designed for flexibility.

j-towns/j-towns.github.io

j-towns/vdvae

Repository for the paper "Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Images"

j-towns/vANS

Formally verified implementation of asymmetric numeral systems (ANS)

j-towns/agda-prelude

Programming library for Agda

j-towns/autograd

Efficiently computes derivatives of numpy code.

j-towns/bazel

a fast, scalable, multi-language and extensible build system

j-towns/bits-back

j-towns/dask

Versatile parallel programming with task scheduling

j-towns/dotfiles

j-towns/jax

GPU- and TPU-backed NumPy with differentiation and JIT compilation.

j-towns/jaxnet

Alternative to TensorFlow2/Keras/PyTorch for more concise, robust and optimized deep learning code

j-towns/jtex

j-towns/learning-to-learn

Learning to Learn in TensorFlow

j-towns/numpy

Numpy main repository

j-towns/plfa.github.io

An introduction to programming language theory in Agda

j-towns/pointy-stax

j-towns/pymanopt

Python toolbox for optimization on manifolds with support for automatic differentiation

j-towns/qr-derivative

j-towns/tensorflow

Computation using data flow graphs for scalable machine learning

j-towns/twenty-fifty

The old web front end to the DECC 2050 Pathways Calculator Excel Model. The new code is at https://github.com/decc/twenty-fifty-new-look. See the old code working at: http://old-interface.2050.org.uk

j-towns/ucl-latex-thesis-templates

UCL LaTeX thesis templates.