PSYCH 2H03 Chapter Notes - Chapter 14: Bigram, Visual Cortex, Object Model
1 Mar 2020
School
Department
Course
Professor
Document Summary
Earlier discussion about the classic" feature net version but other versions exist: modern research offering improvements on the original net. Original model: says activation of one detector serves to activate other detectors. In this model: detectors inhibit one another so activation of one detector decreases activation of others. Attributes of this net make it possible to accomplish recognition without bigram detectors. Also designed for accounting how people recognize printed language; but what about objects? (see theory below: recognition by components (rbc model by hummel and biederman) Objects can also be recognized by a feature network. The intermediate level of detectors = sensitive to geons (geometric ions: idea: geons serve as building blocks for all the objects we recognize. Biederman: we only need 30 geons to describe every object in the world. Approach that ays people have stored in memory a number of different views of each object they can recognize.
