项目作者: huseinzol05
项目描述 :
Gathers Machine learning models using pure Numpy to cover feed-forward, RNN, CNN, clustering, MCMC, timeseries, tree-based, and so much more!
高级语言: Jupyter Notebook
项目地址: git://github.com/huseinzol05/Machine-Learning-Numpy.git
Machine-Learning-Numpy
Code Machine learning models without any frameworks, Numpy only.

Table of contents
Neural Network
Deep Feed-forward
- gradient descent
- momentum
- nesterov
- rmsprop
- adagrad
- adam
Vanilla recurrent
- gradient descent
- momentum
- nesterov
- rmsprop
- adagrad
- adam
Long-short-term-memory recurrent
- gradient descent
- momentum
- nesterov
- rmsprop
- adagrad
- adam
gated-recurrent-unit recurrent
- gradient descent
- momentum
- nesterov
- rmsprop
- adagrad
- adam
Convolutional
- atrous 1D
- atrous 2D
- average pooling 1D
- average pooling 2D
- convolution 1D
- convolution 2D
- max pooling 1D
- max pooling 2D
batch-normalization
- Dropout
- Regularization
Neuro-evolution
- Iris classification
- Iris classification + Novelty search
- Regression
Evolution-strategy
Clustering
- DBScan
- K-Mean
- K-Nearest Neighbors
Decomposition
- Latent Dirichlet Allocation
- Latent Semantic Analysis
- Linear Decomposition Analysis
- Non-negative Matrix Feature
- Principal Component Analysis
- TSNE
Probabilistic
- Gaussian TF-IDF
- Multinomial TF-IDF
- Hidden Markov
- Neural Network
Regression
- Linear
- Polynomial
- Lasso
- Ridge
- Sigmoid logistic
Trees based
- Decision Tree
- Random Forest
- Adaptive Boosting
- Bagging
- Gradient Boosting
Timeseries
- Moving Average
- Linear Weight Moving Average
- John-Ehlers
- Noise Removal-Get
- Anchor Smoothing
- Detect Outliers
- ARIMA
- Seasonal Decomposition
Signal processing
- Convolutional 1D
- Convolutional 2D
- Pass-Filters
Monte-carlo
- Markov Chain
- metropolis hasting normal distribution
- metropolis hasting stock forecasting
- Pi estimation
- Stock market prediction
Discussions
Some of results are not good because of softmax and cross entropy functions I code.
If found any error on my chain-rules, feel free to branch.