Hmshuai's repositories
Machine-Learning
:zap:机器学习实战（Python3）：kNN、决策树、贝叶斯、逻辑回归、SVM、线性回归、树回归
Active-Learning-Bayesian-Convolutional-Neural-Networks
Active Learning on Image Data using Bayesian ConvNets
ActiveHARNet
ActiveHARNet: Towards On-Device Deep Bayesian Active Learning for Human Activity Recognition
bank_interview
:bank: 银行笔试面试经验分享及资料分享（help you pass the bank interview, and get a amazing bank offer!）
CVPR19_Incremental_Learning
Learning a Unified Classifier Incrementally via Rebalancing
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。
DropoutUncertaintyExps
Experiments used in "Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning"
EduCnblogs
This is a project to realize the mobile client for edu.cnblogs.com.
ELIS
Efficient Learning Interpretable Shapelets for Accurate Time Series Classification, ICDE 2018
Hello-world
New study
Human-Activity-Recognition-with-Neural-Network-using-Gyroscopic-and-Accelerometer-variables
The VALIDATION ACCURACY is BEST on KAGGLE. Artificial Neural Network with a validation accuracy of 97.98 % and a precision of 95% was achieved from the data to learn (as a cellphone attached on the waist) to recognise the type of activity that the user is doing. The dataset's description goes like this: The sensor signals (accelerometer and gyroscope) were pre-processed by applying noise filters and then sampled in fixed-width sliding windows of 2.56 sec and 50% overlap (128 readings/window). The sensor acceleration signal, which has gravitational and body motion components, was separated using a Butterworth low-pass filter into body acceleration and gravity. The gravitational force is assumed to have only low frequency components, therefore a filter with 0.3 Hz cutoff frequency was used.
Machine-Learning-in-Action-Python3
《机器学习实战》python3源码
machinelearning
My blogs and code for machine learning. http://cnblogs.com/pinard
monte_carlo_dropout
Uncertainty estimation in deep learning using monte carlo dropout with keras