Stars
A playbook for systematically maximizing the performance of deep learning models.
Pruna is a model optimization framework built for developers, enabling you to deliver faster, more efficient models with minimal overhead.
The Zebrafish Activity Prediction Benchmark measures progress on the problem of predicting cellular-resolution neural activity throughout an entire vertebrate brain.
Official implementation of Laplace-Approximated Neural Additive Models (LA-NAM)
Effortless Bayesian Deep Learning through Laplace Approximation for Flux.jl neural networks.
Keyboard navigation for all of macOS. Click, scroll, and perform tasks with your keyboard.
Bayesian Neural Network Surrogates for Bayesian Optimization
Code for "Invariance Learning in Deep Neural Networks with Differentiable Laplace Approximations"
Repository for the HiRID ICU Benchmark (HiB) project
Code and data for the ACL 2022 paper "Probing as Quantifying Inductive Bias".
Package for causal inference in graphs and in the pairwise settings. Tools for graph structure recovery and dependencies are included.
Second Order Optimization and Curvature Estimation with K-FAC in JAX.
Laplace Redux -- Effortless Bayesian Deep Learning
Figure sizes, font sizes, fonts, and more configurations at minimal overhead. Fix your journal papers, conference proceedings, and other scientific publications.
ASDL: Automatic Second-order Differentiation Library for PyTorch
convert latex to img on google slides
Prettify Python exception output to make it legible.
PyTorch-SSO: Scalable Second-Order methods in PyTorch
Data and code for "Sub-Matrix Factorization for Real-Time Vote Prediction"
An all-atom protein structure dataset for machine learning.
A little Python script to collect LaTeX sources for upload to the arXiv.
BackPACK - a backpropagation package built on top of PyTorch which efficiently computes quantities other than the gradient.
arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv
Python library for real-time vote prediction
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more