This is an introductory course by Caltech Professor Yaser Abu-Mostafa on machine learning that covers the basic theory, algorithms, and applications. Machine learning (ML) enables computational systems to adaptively improve their performance with experience accumulated from the observed data. ML techniques are widely applied in engineering, science, finance, and commerce to build systems for which we do not have full mathematical specification (and that covers a lot of systems). The course balances theory and practice, and covers the mathematical as well as the heuristic aspects.
The Learning Problem - Introduction; supervised, unsupervised, and reinforcement learning. Components of the learning problem.
Error and Noise - The principled choice of error measures. What happens when the target we want to learn is noisy.
Training versus Testing - The difference between training and testing in mathematical terms. What makes a learning model able to generalize?
Theory of Generalization - How an infinite model can learn from a finite sample. The most important theoretical result in machine learning.
The VC Dimension - A measure of what it takes a model to learn. Relationship to the number of parameters and degrees of freedom.
Bias-Variance Tradeoff - Breaking down the learning performance into competing quantities. The learning curves.
The Linear Model II - More about linear models. Logistic regression, maximum likelihood, and gradient descent.
Neural Networks - A biologically inspired model. The efficient backpropagation learning algorithm. Hidden layers.
Overfitting - Fitting the data too well; fitting the noise. Deterministic noise versus stochastic noise.
Regularization - Putting the brakes on fitting the noise. Hard and soft constraints. Augmented error and weight decay.
Validation - Taking a peek out of sample. Model selection and data contamination. Cross validation.
Support Vector Machines - One of the most successful learning algorithms; getting a complex model at the price of a simple one.
Kernel Methods - Extending SVM to infinite-dimensional spaces using the kernel trick, and to non-separable data using soft margins.
Radial Basis Functions - An important learning model that connects several machine learning models and techniques.
Three Learning Principles - Major pitfalls for machine learning practitioners; Occam's razor, sampling bias, and data snooping.