AI Research

A useful way to group algorithms is by their similarity in structure or learning style.

Below are 5 classes of machine learning algorithm that can be used to group algorithms by structure and learning style and 3 examples of algorithms for each class.

Regression: linear regression, logistic regression and stepwise regression.

Instance-based Methods: k-nearest neighbor, learning vector quantization and self-organizing map.

Decision Tree Learning: C4.5, CART and ID3.

Kernel Methods: support vector machine, radial basis network and linear discriminant analysis.

Artificial Neural Networks: perceptron, hopfield and back-propagation.

There are a lot of algorithms out there but a simple structure to group algorithms can help you think about and select the right algorithm for your problem.

A Tour of Machine Learning Algorithms

Reinforcement Q-Learning in Python

Q-learning is an algorithm that can be used to solve some types of RL problems. Q-values are defined for states and actions. Link

DeepSORT: Deep Learning to Track Custom Objects in a Video

Object Detection has seen several recent developments and reached a wide audience but a very important and not widely known extension of the OD is its applications in Object Tracking. Link

Decision Trees Explanation with Online Game (Akinator)

Automotive Insurance with TensorFlow:

O'REILLY Python Data Science Handbook - Link