CGSC170 Study Guide - Midterm Guide: Artificial Neural Network, Fault Tolerance, Synaptic Plasticity

• School: University of Delaware
• Department: Cognitive Science
• Course: CGSC170
• Professor: Andreasen Robin

Document Summary

Mind as artificial neural network (ann)/ connectionism: cognitive activity is modeled (on a computer) in terms of the connections of many simple neuron-like structures (known as artificial neural networks) capable of learning, graceful degradation, and parallel distributed processing. Neurological learning: requires synaptic plasticity and involves an alteration (strengthening or weakening) of a neural pathway/s. Graceful degradation: the ability of a system or network to maintain limited functionality even when a large portion of it has been destroyed: ex: christmas lights, human with brain damage. Parallel processing: multiple computing units perform their calculations simultaneously ex: memory system and language system. Distributed processing: each unit can receive and transmit multiple inputs and outputs: distributed computing is about mastering uncertainty. **neurotransmitter: chemical signals that are released by one neuron and affect the properties of other neurons bind to receptors on the dendrites or the cell body of a neuron. **synaptic cleft: the small gap between neurons where neurotransmitters are released.