Ai-lect14 - Artificial Neural Networks and AI Artificial Neural Networks provide A new computing paradigm A technique for developing trainable

Info iconThis preview shows pages 1–14. Sign up to view the full content.

View Full Document Right Arrow Icon
1 Artificial Neural Networks and AI Artificial Neural Networks provide… - A new computing paradigm - A technique for developing trainable classifiers, memories,  dimension-reducing mappings, etc - A tool to study brain function
Background image of page 1

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

View Full DocumentRight Arrow Icon
2 Converging Frameworks Artificial intelligence (AI):   build a  “packet of intelligence” into a machine Cognitive psychology:   explain human behavior by interacting  processes (schemas) “in the head” but not localized in the brain Brain Theory:   interactions of components of the brain -  - computational neuroscience  - neurologically constrained-models and abstracting from  them as both  Artificial intelligence  and   Cognitive psychology: - connectionism: networks of trainable “quasi-neurons” to provide “parallel  distributed models” little constrained by neurophysiology - abstract (computer program or control system) information processing  models
Background image of page 2
3 Vision, AI and ANNs 1940s: beginning of Artificial Neural Networks Σ i   w i x      θ Perceptron learning rule (Rosenblatt, 1962) Backpropagation Hopfield networks (1982) Kohonen self-organizing maps
Background image of page 3

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

View Full DocumentRight Arrow Icon
4 Vision, AI and ANNs 1950s: beginning of computer vision Aim:  give to machines same or better vision capability as ours Drive: AI, robotics applications and factory automation Initially: passive, feedforward, layered and hierarchical process that was just going to provide input to higher reasoning processes (from AI) But soon: realized that could not handle real images 1980s: Active vision:  make the system more robust by allowing the vision to adapt with the ongoing recognition/interpretation
Background image of page 4
5
Background image of page 5

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

View Full DocumentRight Arrow Icon
6
Background image of page 6
7 Major Functional Areas Primary motor: voluntary movement Primary somatosensory: tactile, pain, pressure, position, temp., mvt. Motor association: coordination of complex movements Sensory association: processing of multisensorial information Prefrontal: planning, emotion, judgement Speech center (Broca’s area): speech production and articulation Wernicke’s area: comprehen- sion of speech Auditory: hearing Auditory association: complex auditory processing Visual: low-level vision Visual association: higher-level vision
Background image of page 7

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

View Full DocumentRight Arrow Icon
8 Interconnect
Background image of page 8
9 More on Connectivity
Background image of page 9

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

View Full DocumentRight Arrow Icon
10 Neurons and Synapses
Background image of page 10
11 Electron Micrograph of a Real Neuron
Background image of page 11

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

View Full DocumentRight Arrow Icon
12 Transmenbrane Ionic Transport Ion channels  act as gates that allow or block the flow of specific  ions into and out of the cell.
Background image of page 12
13 The Cable Equation See  http://diwww.epfl.ch/~gerstner/SPNM/SPNM.html for excellent additional material (some reproduced here). Just a piece of passive dendrite can yield complicated differential 
Background image of page 13

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

View Full DocumentRight Arrow Icon
Image of page 14
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 01/20/2011 for the course CS 6810 taught by Professor Hecker during the Spring '10 term at CSU East Bay.

Page1 / 50

Ai-lect14 - Artificial Neural Networks and AI Artificial Neural Networks provide A new computing paradigm A technique for developing trainable

This preview shows document pages 1 - 14. Sign up to view the full document.

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