* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project
Download Intro-ANN - Computer Science
Activity-dependent plasticity wikipedia , lookup
Human brain wikipedia , lookup
Binding problem wikipedia , lookup
Brain–computer interface wikipedia , lookup
Computer vision wikipedia , lookup
Selfish brain theory wikipedia , lookup
Haemodynamic response wikipedia , lookup
Neural oscillation wikipedia , lookup
Donald O. Hebb wikipedia , lookup
Brain morphometry wikipedia , lookup
Clinical neurochemistry wikipedia , lookup
Brain Rules wikipedia , lookup
Neurolinguistics wikipedia , lookup
History of neuroimaging wikipedia , lookup
Central pattern generator wikipedia , lookup
Artificial intelligence wikipedia , lookup
Neuroplasticity wikipedia , lookup
Neuroesthetics wikipedia , lookup
Neuropsychology wikipedia , lookup
Neural correlates of consciousness wikipedia , lookup
Pattern recognition wikipedia , lookup
Cognitive neuroscience wikipedia , lookup
Optogenetics wikipedia , lookup
Convolutional neural network wikipedia , lookup
Neuroinformatics wikipedia , lookup
Neuroeconomics wikipedia , lookup
Holonomic brain theory wikipedia , lookup
Mind uploading wikipedia , lookup
Artificial general intelligence wikipedia , lookup
Neurophilosophy wikipedia , lookup
Neuroanatomy wikipedia , lookup
Channelrhodopsin wikipedia , lookup
Artificial neural network wikipedia , lookup
Development of the nervous system wikipedia , lookup
Neuropsychopharmacology wikipedia , lookup
Neural engineering wikipedia , lookup
Neural binding wikipedia , lookup
Nervous system network models wikipedia , lookup
Types of artificial neural networks wikipedia , lookup
CS 4700: Foundations of Artificial Intelligence Prof. Carla P. Gomes [email protected] Module: Intro Neural Networks (Reading: Chapter 20.5) Carla P. Gomes CS4700 Neural Networks Rich history, starting in the early forties with McCulloch and Pitts’s model of artificial neurons (McCulloch and Pitts 1943). Two views: – Modeling the brain – “Just” representation of complex functions (Continuous; contrast decision trees) Much progress on both fronts. Drawn interest from: Neuroscience, Cognitive science, AI, Physics, Statistics, and CS/EE. Carla P. Gomes CS4700 Computer processor speed (MIPS) Computer vs. Brain Circa 1997 Information or computer storage (Megabytes) Increasing Compute Power: Moore’s Law The world's first 2-billion transistor microprocessor delivered in next-generation Intel® Itanium® processors codenamed Tukwila Tukwila is targeted for production towards the end of 2008. In 1965, Gordon Moore, Intel co-founder, predicted that the number of transistors on a chip would double about every two years. (popularly known as Moore's Law). Intel has kept that pace for nearly 40 years. Carla P. Gomes CS4700 Computer processor speed (MIPS) Computer Power / Cost Circa 1997 Neural Networks Computational model inspired by the brain Brain based on the interaction of multiple connected processing elements (Connectionism, parallel distributed processing, neural computation) . When inputs reach some threshold an action potential Inputs (electric pulse) is sent along the axon to the outputs Outputs Brain made up Brain’s information 11 of neurons (~10 ) and processing power emerges from a highly interconnected network of neurons. Around 1011 neurons, 1014 synapses; a cycle time of 1ms-10 ms. Connection between cells Excitatory or inhibitory and may change over time Carla P. Gomes CS4700 Connectionist Models of Learning Characterized by: A large number of very simple neuron-like processing elements. A large number of weighted connections between the elements. Highly parallel, distributed control. An emphasis on learning internal representations automatically. But of course the interconnectivity is not really at the brain scale… Carla P. Gomes CS4700 Autonomous Learning Vehicle In a Neural Net (ALVINN) ALVINN learns to drive an autonomous vehicle at normal speeds on public highways. ALVINN is a perception systems which learns to control the NAVLAB vehicles by watching a person drive. Pomerleau et al, 1993 Carla P. Gomes CS4700 ALVINN drives 70mph on highways 30 x 32 grid of pixel intensities from camera Each output unit correspond to a particular steering direction. The most highly activated one gives the direction to steer. What kinds of problems are suitable for neural networks? Have sufficient training data Long training times are acceptable Not necessary for humans to understand learned target function or hypothesis neural networks are magic black boxes Carla P. Gomes CS4700 Tasks – Function approximation, or regression analysis, including time series prediction and modeling. – Classification, including pattern and sequence recognition, novelty detection and sequential decision making. – Data processing, including filtering, clustering, blind signal separation and compression. Carla P. Gomes CS4700 Example of Application Areas Application areas include: • • • • • • • • • System identification and control (vehicle control, process control), Game-playing and decision making (backgammon, chess, racing), Pattern recognition (radar systems, face identification, object recognition, etc.) Sequence recognition (gesture, speech, handwritten text recognition), Medical diagnosis Financial applications Data mining (or knowledge discovery in databases, "KDD"), Visualization E-mail spam filtering. Carla P. Gomes CS4700