Machine Learning

MACHINE LEARNING

Machine Learning is the study of algorithms that improve their performance at some task with experience

•       Optimize a performance criterion using example data or past experience (heuristics)

•       Role of Statistics: inference from a sample

•       Role of Computer science: efficient algorithms to

•       Solve the optimization problem

•       Representing and evaluating the model for inference

Similarly, Machine learning is also defined as the AI field of programming computers to optimize a performance criterion using example data or past experience; e.g., there is no need to “learn” to calculate payroll.  Instead, learning is used when:

•       Humans are unable to explain their expertise (speech recognition)

•       Human expertise does not exist (navigating on Mars),

•       Solution changes in time (routing on a computer network)

•       Solution needs to be adapted to particular cases (user biometrics).

I will discuss both Supervised and Unsupervised ML Methods and approaches to both Discriminative and Generative Models.

An example of Machine Learning utilizing neural networks in autonomous driving.  A video of the ALVINN autonomous  driving car is presented here. To read more about ALVINN, click here.

To download this presentation's slides, click here.