Machine Learing (ML)

Machine learning is an application of artificial intelligence (AI) that provides systems the ability to automatically learn and improve from experience without being explicitly programmed. Machine learning focuses on the development of computer programs that can access data and use it to learn for themselves.

For beginners Machine Learning by Google and Machine Learning by scikit-learn will be a good take-off.
To start understanding most of the Machine Learning algorithms, you must get the basic understanding of Calculus and Linear Algebra:

• Linear Algebra
• Calculus
• Derivatives exersices
• Derivatives exersices
• Partial Derivatives
• Partial Derivatives exersices

When there is a clear understanding how Deep Learning is working nor used on data.
Supervised Learning, Unsupervised Learning and Reinforcement Learning are understandable as well.

Requirements

  # (required to have programming knowledge)
  # 1 - open a command prompt, in this folder.
  # 2 - paste line below & press enter.
  pip3 install -r "./requirements.txt"

Deep Learning

Usage Type	Model Type	tensorflow	pytorch	numpy
Artificial Neural Networks
	Perceptron	⬜️	⬜️	✅
	Feed Forward	✅	⬜️	✅
	Deep Feed Forward	✅	✅	✅
	Radial Basis Network	⬜️	✅	✅
Recurrent Neural Networks
	Recurrent Neural Network	✅	✅	✅
	Long Short Term Memory	✅	✅	⬜️
	Gated Recurrent Unit	✅	✅	⬜️
Auto Encoders
	Auto Encoder	✅	✅	✅
	Denoising Autoencoder	✅	✅	✅
	Generative Adversarial Network	✅	✅	✅
	Sparse Autoencoder	✅	✅	⬜️
	Variational Autoencoder	✅	✅	⬜️
Convolution Neural Networks
	Deep Convolutional Network	✅	✅	✅
	Deconvolutional Network	✅	✅	⬜️
	Deep Convolutional Inverse Graphics Network	✅	✅	✅
Stochastic Neural Networks
	Deep Belief Network	⬜️	✅	⬜️
	Restricted Boltzmann Machine	⬜️	✅	✅
Reservoir Computing
	Liquid State Machine	⬜️	⬜️	⬜️
	Extreme Learning Machine	⬜️	⬜️	✅
	Echo State Network	⬜️	⬜️	✅
Ungrouped Networks
	Deep Residual Network	✅	✅	⬜️
	Kohonen Network	⬜️	✅	⬜️
	Neural Tuning Machine	⬜️	✅	⬜️
	Support Vector Machine	⬜️	⬜️	✅

Supervised Learning

Usage Type	Model Type	numpy
Classification
	Binary Classification	✅
	Imbalanced Classification	✅
	Multi Class Classification	✅
	Multi Label Classification	✅
Regression
	Cox Regression	✅
	Elastic Net Regression	✅
	Lasso Regression	✅
	Linear Regression	✅
	Logistic Regression	✅
	Negative Binomial Regression	✅
	Ordinal Regression	✅
	Partial Least Squares Regression	✅
	Poisson Regression	✅
	Polynomial Regression	✅
	Principal Components Regression	✅
	Quantile Regression	✅
	Ridge Regression	✅
	Support Vector Regression	✅

Unsupervised Learning

Usage Type	Model Type	sample	numpy
Clustering
	Affinity Propagation	✅	✅
	Agglomerative Clustering	✅	✅
	BIRCH	✅	⬜️
	DBSCAN	✅	✅
	Gaussian Mixture	✅	✅
	K-Means	✅	✅
	Mean Shift	✅	✅
	OPTICS	✅	✅
	Spectral Clustering	✅	✅
Dimensionality Reduction
	Latent Semantic Analysis	✅	⬜️
	Non Negative Matrix Factorization	✅	⬜️
	Principal Component Analysis	✅	✅
	T-Distributed Stochastic Neighbor Embedding	✅	⬜️
	Uniform Manifold Approximation And Projection	✅	⬜️

Reinforcement Learning

Model Type	sample
Q-Learning	✅
Deep Q-Learning	✅
Double Deep Q-Learning	✅
Actor Critic Method	✅
Deep Deterministic Policy Gradient	✅
Proximal Policy Optimization	✅

Usefull Resources:

• https://www.youtube.com/user/stanfordonline
• https://www.youtube.com/channel/UC58v9cLitc8VaCjrcKyAbrw
• https://developers.google.com/machine-learning
• https://machinelearningmastery.com
• https://gluon.mxnet.io/
• https://pub.towardsai.net
• https://atcold.github.io/pytorch-Deep-Learning
• https://www.datatechnotes.com/

Kind Regards,
Niek Tuytel :)