blue-one's starred repositories
transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
pumpkin-book
《机器学习》(西瓜书)公式详解
Dive-into-DL-PyTorch
本项目将《动手学深度学习》(Dive into Deep Learning)原书中的MXNet实现改为PyTorch实现。
leedl-tutorial
《李宏毅深度学习教程》(李宏毅老师推荐👍),PDF下载地址:https://github.com/datawhalechina/leedl-tutorial/releases
the-economist-ebooks
经济学人(含音频)、纽约客、自然、新科学人、卫报、科学美国人、连线、大西洋月刊、国家地理等英语杂志免费下载,支持epub、mobi、pdf格式, 每周更新.
anomaly-detection-resources
Anomaly detection related books, papers, videos, and toolboxes
python-small-examples
告别枯燥,致力于打造 Python 实用小例子,更多Python良心教程见 https://ai-jupyter.com
MachineLearning_Python
机器学习算法python实现
berkeley-stat-157
Homepage for STAT 157 at UC Berkeley
zihao_course
同济子豪兄的公开课
Machine-Learning
机器学习原理
fancyimpute
Multivariate imputation and matrix completion algorithms implemented in Python
News-Record
目前主要维护经济学人【The Economist】、纽约客【The NewYorker】和时代杂志【Time】
Physics-Informed-Neural-Networks
Investigating PINNs
LibADMM-toolbox
A Library of ADMM for Sparse and Low-rank Optimization
SGDLibrary
MATLAB/Octave library for stochastic optimization algorithms: Version 1.0.20
pinns-torch
PINNs-Torch, Physics-informed Neural Networks (PINNs) implemented in PyTorch.
MATLAB-NS3
MATLAB and NS3 co-simulation
ELMToolbox
Matlab implementation of Extreme Learning Machine and variants
FRSVT
I implemented the fllowing article by Matlab.Refrence:Oh T H, Matsushita Y, Tai Y W, et al. Fast Randomized Singular Value Thresholding for Low-rank Optimization[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2015, PP(99):1-1.Abstract:Rank minimization can be converted into tractable surrogate problems, such as Nuclear Norm Minimization (NNM) and Weighted NNM (WNNM). The problems related to NNM, or WNNM, can be solved iteratively by applying a closed-form proximal operator, called Singular Value Thresholding (SVT), or Weighted SVT, but they suffer from high computational cost of Singular Value Decomposition (SVD) at each iteration. We propose a fast and accurate approximation method for SVT, that we call fast randomized SVT (FRSVT), with which we avoid direct computation of SVD. The key idea is to extract an approximate basis for the range of the matrix from its compressed matrix. Given the basis, we compute partial singular values of the original matrix from the small factored matrix. In addition, by developping a range propagation method, our method further speeds up the extraction of approximate basis at each iteration. Our theoretical analysis shows the relationship between the approximation bound of SVD and its effect to NNM
Iteratively-Reweighted-Nuclear-Norm-Minimization
Iteratively Reweighted Nuclear Norm for Nonconvex Nonsmooth Low-rank Minimization
Energy-Efficiency-in-Reinforcement-Learning
Code for the paper 'Energy Efficiency in Reinforcement Learning for Wireless Sensor Networks'
WSNsimulatorMatlab
Develop Simple and Efficient WSN Simulator for Researchers Version 1.0
Hole-and-Boundary-node-detection
Hole and Boundary node detection in wireless sensor network (WSN)
IoTanomalydetection
This is a system design for an anomaly detection pipeline for a WSN implemented on Arduino boards and Raspberry Pi