Kohsin

cifar10_cnn

用Keras实现CIFAR-10图片分类

CLEVER-TF-Keras

Re-Implementation of [Cross-Lipschitz Extreme Value for nEtwork Robustness](https://github.com/huanzhang12/CLEVER) with Keras and TensorFlow

DomainDrivenRegReg

dynamical-isometry

Investivating dynamical isometry as described in: https://arxiv.org/pdf/1711.04735.pdf

Dynamical-Isometry-from-Orthogonality-Neural-Nets

Mathematical consequences of orthogonal weights initialization and regularization in deep learning. Experiments with gain-adjusted orthogonal regularizer on RNNs with SeqMNIST dataset.

EchoStateNetwork

A simple Python implementation of EchoStateNetwork

ESN

expRNN

Optimization with orthogonal constraints and on general manifolds

GLISTA

source code of GLISTA

Goal-SAR

Official code for the Paper "Goal-driven Self-Attentive Recurrent Networks for Trajectory Prediction", CVPRW 2022

Kohsin/cifar10_cnn

用Keras实现CIFAR-10图片分类

Kohsin/CLEVER-TF-Keras

Re-Implementation of [Cross-Lipschitz Extreme Value for nEtwork Robustness](https://github.com/huanzhang12/CLEVER) with Keras and TensorFlow

Kohsin/DomainDrivenRegReg

Kohsin/dynamical-isometry

Investivating dynamical isometry as described in: https://arxiv.org/pdf/1711.04735.pdf

Kohsin/Dynamical-Isometry-from-Orthogonality-Neural-Nets

Mathematical consequences of orthogonal weights initialization and regularization in deep learning. Experiments with gain-adjusted orthogonal regularizer on RNNs with SeqMNIST dataset.

Kohsin/EchoStateNetwork

A simple Python implementation of EchoStateNetwork

Kohsin/ESN

Kohsin/expRNN

Optimization with orthogonal constraints and on general manifolds

Kohsin/GLISTA

source code of GLISTA

Kohsin/Goal-SAR

Official code for the Paper "Goal-driven Self-Attentive Recurrent Networks for Trajectory Prediction", CVPRW 2022

Kohsin/HTR

Kohsin/ivts-ijcnn2024

Kohsin/liquid_time_constant_networks

Code Repository for Liquid Time-Constant Networks (LTCs)

Kohsin/mctorch

A manifold optimization library for deep learning

Kohsin/neurodiffeq

A library for solving differential equations using neural networks based on PyTorch, used by multiple research groups around the world, including at Harvard IACS.

Kohsin/ng-rc-paper-code

Code for the paper "Next Generation Reservoir Computing"

Kohsin/NN-CUDA-Example

Several simple examples for popular neural network toolkits calling custom CUDA operators.

Kohsin/Orthogonal-Convolutional-Neural-Networks

Code for paper "Orthogonal Convolutional Neural Networks".

Kohsin/Orthogonality-in-CNNs

[NeurIPS '18] "Can We Gain More from Orthogonality Regularizations in Training Deep CNNs?" Official Implementation.

Kohsin/pointMLP-pytorch

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

Kohsin/Pointnet_Pointnet2_pytorch

PointNet and PointNet++ implemented by pytorch (pure python) and on ModelNet, ShapeNet and S3DIS.

Kohsin/power_law

Kohsin/pymanopt

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

Kohsin/pytorch-Jacobian

Implement efficient jacobian method available for most pytorch networks

Kohsin/sequencer

Sequencer: Deep LSTM for Image Classification

Kohsin/SODEF

Kohsin/torchdiffeq

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

Kohsin/VARS

Official code for `Visual Attention Emerges from Recurrent Sparse Reconstruction' (ICML 2022)

Kohsin/ViR