Motivation and Overview

tripastroturfΤεχνίτη Νοημοσύνη και Ρομποτική

7 Νοε 2013 (πριν από 3 χρόνια και 5 μήνες)

70 εμφανίσεις

Daphne Koller

Introduction

Motivation
and Overview

Probabilistic

Graphical

Models

Daphne Koller

Probabilistic

Graphical

Models

Daphne Koller

Daphne Koller

Models


Daphne Koller

Uncertainty


Partial knowledge of
state
of the
world



Noisy
observations



Phenomena not covered by our
model



Inherent
stochasticity

Daphne Koller

Probability Theory


Declarative representation with clear
semantics



Powerful reasoning patterns



E
stablished learning methods

Daphne Koller

Complex Systems

Daphne Koller

Graphical Models

Intelligence

Difficulty

Grade

Letter

SAT

B

D

C

A

Bayesian networks

Markov networks

Daphne Koller

Graphical Models

Daphne Koller

Graphical Models


Graphical representation:


intuitive & compact data structure


efficient reasoning using general algorithms


can be learned from limited data

Daphne Koller

Many Applications


Medical diagnosis


Fault diagnosis


Natural language
processing


Traffic analysis


Social network models


Message decoding



Computer vision


Image segmentation


3D reconstruction


Holistic scene analysis


Speech recognition


Robot localization &
mapping


Daphne Koller

END END END

Template

vertLeftWhite1

Suppose
q

is at a local minimum of a
function. What will one iteration of
gradient descent do?

Leave
q

unchanged.

Change
q

in a random direction.

Move
q

towards the global minimum of J(
q
).

Decrease
q
.

Template

vertLeftWhite1

Consider the weight update:


Which of these is a correct vectorized implementation?

Template

vertLeftWhite2

Fig. A corresponds to
a
=0.01, Fig. B to
a
=0.1, Fig. C to
a
=1.

Fig. A corresponds to
a
=0.1, Fig. B to
a
=0.01, Fig. C to
a
=1.

Fig. A corresponds to
a
=1, Fig. B to
a
=0.01, Fig. C to
a
=0.1.

Fig. A corresponds to
a
=1, Fig. B to
a
=0.1, Fig. C to
a
=0.01.

Template

vertLeftWhite2


Template

block2x2White1


Ordering of

buttons is:

13

24