|
Lecture

# Training Versus Testing

Home > Computer Science > Artificial Intelligence > Machine Learning > Training Versus Testing Lecture Details:

Training versus Testing - The difference between training and testing in mathematical terms. What makes a learning model able to generalize?

Lectures:
• ### The Learning Problem

01:21:33Yaser Abu-Mostafa

The Learning Problem - Introduction; supervised, unsupervised, and reinforcement learning. Components of the learning problem.

• ### Error and Noise

01:18:22Yaser Abu-Mostafa

Error and Noise - The principled choice of error measures. What happens when the target we want to learn is noisy.

• ### Training Versus Testing

01:16:58Yaser Abu-Mostafa

Training versus Testing - The difference between training and testing in mathematical terms. What makes a learning model able to generalize?

• ### Theory of Generalization

01:18:12Yaser Abu-Mostafa

Theory of Generalization - How an infinite model can learn from a finite sample. The most important theoretical result in machine learning.

• ### The VC Dimension

01:13:31Yaser Abu-Mostafa

The VC Dimension - A measure of what it takes a model to learn. Relationship to the number of parameters and degrees of freedom.

01:16:51Yaser Abu-Mostafa

Bias-Variance Tradeoff - Breaking down the learning performance into competing quantities. The learning curves.

• ### The Linear Model II

01:27:14Yaser Abu-Mostafa

The Linear Model II - More about linear models. Logistic regression, maximum likelihood, and gradient descent.

• ### Neural Networks

01:25:16Yaser Abu-Mostafa

Neural Networks - A biologically inspired model. The efficient backpropagation learning algorithm. Hidden layers.

• ### Overfitting

01:19:49Yaser Abu-Mostafa

Overfitting - Fitting the data too well; fitting the noise. Deterministic noise versus stochastic noise.

• ### Regularization

01:15:14Yaser Abu-Mostafa

Regularization - Putting the brakes on fitting the noise. Hard and soft constraints. Augmented error and weight decay.

• ### Validation

01:26:12Yaser Abu-Mostafa

Validation - Taking a peek out of sample. Model selection and data contamination. Cross validation.

• ### Support Vector Machines

01:14:16Yaser Abu-Mostafa

Support Vector Machines - One of the most successful learning algorithms; getting a complex model at the price of a simple one.

• ### Kernel Methods

01:18:19Yaser Abu-Mostafa

Kernel Methods - Extending SVM to infinite-dimensional spaces using the kernel trick, and to non-separable data using soft margins.

01:22:08Yaser Abu-Mostafa

Radial Basis Functions - An important learning model that connects several machine learning models and techniques.

• ### Three Learning Principles

01:16:18Yaser Abu-Mostafa

Three Learning Principles - Major pitfalls for machine learning practitioners; Occam's razor, sampling bias, and data snooping.

• ### Epilogue

01:09:28Yaser Abu-Mostafa

Epilogue - The map of machine learning. Brief views of Bayesian learning and aggregation methods.