1 / 15

Cogs 118A: Natural Computation I Angela Yu ajyu@ucsd January 6, 2008

Cogs 118A: Natural Computation I Angela Yu ajyu@ucsd.edu January 6, 2008. http://www.cogsci.ucsd.edu/~ajyu/Teaching/Cogs118A_wi09/cogs118A.html. Course Overview. Statistical methods. assignments. Neural networks. Advanced topics. midterm. Applications to cognitive science. final project.

gay
Download Presentation

Cogs 118A: Natural Computation I Angela Yu ajyu@ucsd January 6, 2008

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Cogs 118A: Natural Computation IAngela Yuajyu@ucsd.eduJanuary 6, 2008 http://www.cogsci.ucsd.edu/~ajyu/Teaching/Cogs118A_wi09/cogs118A.html

  2. Course Overview Statistical methods assignments Neural networks Advanced topics midterm Applications to cognitive science final project

  3. Supervised learning The agent also observes a seqence of labels or outputsy1, y2, …, and the goal is to learn the mapping f: x  y. Unsupervised learning The agent’s goal is to learn a statistical model for the inputs, p(x), to be used for prediction, compact representation, decisions, … Reinforcement learning The agent can perform actions a1, a2, a3, …, which affect the state of the world, and receives rewards r1, r2, r3, … Its goal is to learn a policy: {x1, x2, …, xt} atthat maximizes rewards. Three Types of Learning Imagine an agent observes a sequence of of inputs: x1, x2, x3, …

  4. Cat Dog y x Supervised Learning Classification: the outputs y1, y2, … are discrete labels Regression: the outputs y1, y2, … are continuously valued

  5. Object Categorization Speech Recognition VET WET Face Recognition Motor Learning Applications: Cognitive Science

  6. Motor Learning Challenges • Noisy sensory inputs • Incomplete information • Changing environment • Many variables (mostly irrelevant) • No (one) right answer • Prior knowledge • Inductive inference (open-ended) • Uncertainty, not deterministic

  7. An Example: Curve-Fitting y x

  8. Error function (root-mean-square) Polynomial Curve-Fitting Linear model

  9. Linear Fit? y x

  10. Quadratic Fit? y x

  11. 5th-Order Polynomial Fit? y x

  12. 10th-Order Polynomial Fit? y x

  13. And the Answer is… Quadratic y x

  14. Training Error vs. Test Error 1st-order 2nd-order y 5th-order 10th-order y x x

  15. What Did We Learn? • Model complexity important • Minimizing training error  overtraining • A better error metric: test error • But test error costs extra data (precious) • Fix 1: regularization (3.1) • Fix 2: Bayesian model comparison (3.3)

More Related