mirror of
https://github.com/Relintai/MLPP.git
synced 2025-02-12 16:20:06 +01:00
78 lines
2.3 KiB
Markdown
78 lines
2.3 KiB
Markdown
# ML++
|
|
|
|
Machine learning is a vast and exiciting discipline, garnering attention from specialists of many fields. Unfortunately, for C++ programmers and enthusiasts, there appears to be a lack of support for this magnificient language in the field of machine learning. As a consequence, this library was created in order to fill that void and give C++ a true foothold in the ML sphere to act as a crossroad between low level developers and machine learning engineers.
|
|
|
|
<p align="center">
|
|
<img src="https://user-images.githubusercontent.com/78002988/119920911-f3338d00-bf21-11eb-89b3-c84bf7c9f4ac.gif"
|
|
width = 600 height = 400>
|
|
</p>
|
|
|
|
## Contents of the Library
|
|
1. ***Regression***
|
|
1. Linear Regression
|
|
2. Logistic Regression
|
|
3. Softmax Regression
|
|
4. Exponential Regression
|
|
5. Probit Regression
|
|
6. CLogLog Regression
|
|
2. ***Deep, Dynamically Sized Neural Networks***
|
|
1. Possible Activation Functions
|
|
- Linear
|
|
- Sigmoid
|
|
- Swish
|
|
- Softplus
|
|
- CLogLog
|
|
- Gaussian CDF
|
|
- GELU
|
|
- Unit Step
|
|
- Sinh
|
|
- Cosh
|
|
- Tanh
|
|
- Csch
|
|
- Sech
|
|
- Coth
|
|
- Arsinh
|
|
- Arcosh
|
|
- Artanh
|
|
- Arcsch
|
|
- Arsech
|
|
- Arcoth
|
|
2. Possible Loss Functions
|
|
- MSE
|
|
- RMSE
|
|
- MAE
|
|
- MBE
|
|
- Log Loss
|
|
- Cross Entropy
|
|
- Hinge Loss
|
|
3. Possible Regularization Methods
|
|
- Lasso
|
|
- Ridge
|
|
- ElasticNet
|
|
4. Possible Weight Initialization Methods
|
|
- Uniform
|
|
- Xavier Normal
|
|
- Xavier Uniform
|
|
- He Normal
|
|
- He Uniform
|
|
3. ***Prebuilt Neural Networks***
|
|
1. Multilayer Peceptron
|
|
2. Autoencoder
|
|
3. Softmax Network
|
|
4. ***Natural Language Processing***
|
|
1. Word2Vec (Continous Bag of Words, Skip-N Gram)
|
|
2. Stemming
|
|
3. Bag of Words
|
|
4. TFIDF
|
|
5. Tokenization
|
|
6. Auxiliary Text Processing Functions
|
|
5. ***Computer Vision***
|
|
1. The Convolution Operation
|
|
2. Max, Min, Average Pooling
|
|
3. Global Max, Min, Average Pooling
|
|
4. Prebuilt Feature Detectors
|
|
- Horizontal/Vertical Prewitt Filter
|
|
- Horizontal/Vertical Sobel Filter
|
|
- Horizontal/Vertical Scharr Filter
|
|
- Horizontal/Vertical Roberts Filter
|