introduction

introduction - Probabilistic Models in Cognitive Science...

Info iconThis preview shows pages 1–8. Sign up to view the full content.

View Full Document Right Arrow Icon
Probabilistic Models in Cognitive Science and Artificial Intelligence
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
A Brief History of Cog Sci and AI 1950’s-1980’s Symbolic models of cognition von Neumann computer architecture as metaphor 1980’s-1990’s Connectionist models of cognition Massively parallel neuron-like networks of simple processors as metaphor Late 1990’s -? Probabilistic / statistical models of cognition Formalizes the best of connectionist ideas
Background image of page 2
Relation of Probabilistic Models to Connectionist and Symbolic Models Connectionist models Symbolic models Probabilistic models strong bias principled, elegant incorporation of rule learning from (small # examples) structured representations weak (unknown) bias ad hoc, implicit incorporation of prior statistical learning (large # examples) vector representations
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Two Notions of Probability Frequentist notion Relative frequency obtained if event were observed many times (e.g., coin flip) Subjective notion Degree of belief in some hypothesis Analogous to connectionist activation Long philosophical battle between these two views Subjective notion makes sense for cog sci and AI given that probabilities represent mental states
Background image of page 4
Why Probability? It’s the optimal thing to do, in the sense that any other strategy will lead to lower expected returns e.g., will roll of a die produce number < 4? e.g., should you drive or walk to store? Randomness in the brain and world introduces uncertainty, and so it makes sense to describe uncertainty in the language of random events.
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Rationality in Cognitive Science Some theories in cognitive science are based on premise that human performance is optimal Rational theories, ideal observer theories Ignores biological constraints Probably true in some areas of cognition (e.g., vision) More interesting: bounded rationality Optimality is assumed to be subject to limitations on processing hardware and capacity, representation, experience with the world.
Background image of page 6
Value of Probabilistic Models in Cognitive Science Elegant theories specify brain's limitations such that performance can be cast as optimal subject to these limitations
Background image of page 7

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 8
This is the end of the preview. Sign up to access the rest of the document.

Page1 / 25

introduction - Probabilistic Models in Cognitive Science...

This preview shows document pages 1 - 8. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online