2 lecture_sept16

2 lecture_sept16 - Connectionism in brief Connectionism...

Info iconThis preview shows pages 1–3. Sign up to view the full content.

View Full Document Right Arrow Icon
Copyright Thomas R. Shultz 1 pdp 1 Connectionism pdp 2 Connectionism in brief ± Network of units & weights ± Each unit has simple program ± Compute weighted sum of inputs from other units ± Output a number, a non-linear function of weighted sum of inputs ± Send output to other units doing the same ± Modify weights to reduce error pdp 3 Inspired by neuroscience ± Neurons are sluggish & noisy processing devices ± Yet we perceive & recognize in about .5 sec ± Thus, brain must be a parallel processor pdp 4 Variety of neurons pdp 5 Schematic neuron Cell body Dendrites Axon Synapse pdp 6 Biological neural networks
Background image of page 1

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

View Full DocumentRight Arrow Icon
Copyright Thomas R. Shultz 2 pdp 7 Computational properties of brain ± Robust & fault tolerant ± Flexible ± Approximate ± Highly parallel ± Compact and efficient pdp 8 Network components ± Units ± Activation depends on weighted sum of inputs ± Connections ± Positive or negative ± Weighted pdp 9 Translation: Brain to neural net neuron = activity = synapse = synaptic reception =
Background image of page 2
Image of page 3
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 02/14/2011 for the course PSYC 532 taught by Professor Shultz during the Fall '10 term at McGill.

Page1 / 6

2 lecture_sept16 - Connectionism in brief Connectionism...

This preview shows document pages 1 - 3. Sign up to view the full document.

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