ViewTube

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

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

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

Error and Noise - The principled choice of error measures. What happens when the target we want to learn is noisy. Lecture 4 of ...

This video is part of a series on the following website: https://work.caltech.edu/telecourse.html We don't have any rights on the ...

Is Learning Feasible? - Can we generalize from a limited sample to the entire space? Relationship between in-sample and ...

The Linear Model I - Linear classification and linear regression. Extending linear models through nonlinear transforms. Lecture 3 ...

Overfitting - Fitting the data too well; fitting the noise. Deterministic noise versus stochastic noise. Lecture 11 of 18 of Caltech's ...

Bias-Variance Tradeoff - Breaking down the learning performance into competing quantities. The learning curves. Lecture 8 of 18 ...

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

Regularization - Putting the brakes on fitting the noise. Hard and soft constraints. Augmented error and weight decay. Lecture 12 ...

James Randi lecture excerpt from a 2 hour lecture at Caltech in 1992.

This video is part of a series on the following website: https://work.caltech.edu/telecourse.html We don't have any rights on the ...

The Linear Model II - More about linear models. Logistic regression, maximum likelihood, and gradient descent. Lecture 9 of 18 of ...

View course materials on the course website - http://work.caltech.edu/telecourse.html Produced in association with Caltech ...

View course materials on the course website - http://work.caltech.edu/telecourse.html Produced in association with Caltech ...

This video is part of a series on the following website: https://work.caltech.edu/telecourse.html We don't have any rights on the ...

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

Validation - Taking a peek out of sample. Model selection and data contamination. Cross validation. Lecture 13 of 18 of Caltech's ...

View course materials on the course website - http://work.caltech.edu/telecourse.html Produced in association with Caltech ...