Understanding model fitting is important for understanding the models’ poor accuracy.

Overfitting: When the model performs too well on training data then it reduces the model flexibility for new data.

Underfitting: When the model performs poorly on the training data. It’s often caused by an excessively simple model.

Both overfitting and underfitting lead to poor performance in real time.

Balanced: Bbalanced models would show better accuracy on new data.

Artificial Intelligence:

A branch of computer science dealing with the simulation of intelligent behavior in computers using human behavior such as visual perception, speech recognition, decision-making, and translation between languages. .

Machine Learning:

Basic approach of Machine learning is solving problems using algorithms in three steps “parse data”, “learn from it”, and “make a determination or prediction about something”.

Deep Learning:

Deep learning is a sub-set of machine learning with better accuracy. Deep learning structures algorithms in layers to create an “artificial neural network” that can learn and make intelligent decisions on its own.

Resources:

https://skymind.ai/wiki/ai-vs-machine-learning-vs-deep-learning

https://blogs.nvidia.com/blog/2016/07/29/whats-difference-artificial-intelligence-machine-learning-deep-learning-ai/

What is Machine Learning?

Machine Learning is the branch of computer science for developing algorithms and statistical models which computer systems can use to solve specific type of tasks.

Mathematics for Machine Learning:

• Algebra (Equations, Vectors, Matrices)

• Calculus(Function, Derivatives, Integrals)

• Graphs

• Statistics

• Probability

• Set Theory

Types of Machine Learning?

All machine learning algorithms are categorized into three categories:

• Supervised and semi-supervised learning

• Unsupervised leaning

• Reinforcement learning