[NeurIPS'22] PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies

PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space

[ICLR 2022 poster] Official PyTorch implementation of "Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework"

Kolmogorov Arnold Networks

Kolmogorov Arnold Networks trained on MNIST

PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation

pytorch implementation for "PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation" https://arxiv.org/abs/1612.00593

Code for Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data, ICCV 2019

This repository contains implementations and illustrative code to accompany DeepMind publications

Tensors and Dynamic neural networks in Python with strong GPU acceleration

A PyTorch implementation of L-BFGS.

Parallel Computing and Scientific Machine Learning (SciML): Methods and Applications (MIT 18.337J/6.338J)

Awesome resources for learning control theory

A simple, easy to use MNIST loader written in Python 3

A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API

A collection of resources regarding the interplay between differential equations, deep learning, dynamical systems, control and numerical methods.

SciPy library main repository

A two layer perceptron implemented in MatLab to recognize handwritten digits based on the MNIST dataset.

PyTorch Tutorials from my YouTube channel

Apollo: An Adaptive Parameter-wise Diagonal Quasi-Newton Method for Nonconvex Stochastic Optimization

A fully connected neural network classifier with arbitrary number of hidden layers, different activation functions, etc..

Resources for the book "Introduction to Numerical Methods for Variational Problems" by H. P. Langtangen and K.-A. Mardal

A Vanilla Numpy-only Feed-Forward Neural Network.

Differentiable ODE solvers with full GPU support and O(1)-memory backpropagation.

A pure Matlab implementation of L-BFGS-B (LBFGSB)

Neural nets for high accuracy multivariable nonlinear regression.