mtkwt Goto Github PK
Name: Tetsuya Motokawa
Type: User
Company: https://revisio.co.jp/
Bio: DS@REVISIO Inc.
Name: Tetsuya Motokawa
Type: User
Company: https://revisio.co.jp/
Bio: DS@REVISIO Inc.
Implementation of Adaptive Hessian-free optimization.
Package for CGD and ACGD optimizers
Beginner's guide for C++
Jupyter notebooks for the code samples of the book "Deep Learning with Python"
DeepVis Toolbox
Measurements of Three-Level Hierarchical Structure in the Outliers in the Spectrum of Deepnet Hessians (ICML 2019)
Code for the CVPR 2019 article "Decoupling Direction and Norm for Efficient Gradient-Based L2 Adversarial Attacks and Defenses"
PyTorch implementation of FIM and empirical FIM
Unconstrained function minimization in Javascript
Hessian backpropagation (HBP): PyTorch extension of backpropagation for block-diagonal curvature matrix approximations
Hessian spectral analysis with tensorflow1.x
Some Hessian based analysis for practical deep models with tensorflow2
An implementation of the Hessian-free optimization algorithm in Theano
Hessian-free optimization for deep networks
Hessian Free Optimization with Tensorflow
Deep Learning for humans
An implementation of KFAC for TensorFlow
compilerbookを参考にCコンパイラを自作する
Implementation of numerical algorithms
Numerical Tours of Signal Processing
数理最適化: Optimization Night #8 での発表資料のシミュレーションコード
PyHessian is a Pytorch library for second-order based analysis and training of Neural Networks
Tensors and Dynamic neural networks in Python with strong GPU acceleration
PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO) and Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR).
Pytorch implementation of convolutional neural network visualization techniques
PyTorch implementation of Hessian Free optimisation
PyTorch Kronecker Factored Approximation of the Hessian
Python Implementation of Reinforcement Learning: An Introduction
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.