Beyond Simple and Complex Neurons: Towards Intermediate-level Representations of Shapes and Objects

Knowledge of the brain has much advanced since the concept of the neuron doctrine developed by Ramón y Cajal (R Trim Histol Norm Patol 1:33–49, 1888 ). Over the last six decades a wide range of functionalities of neurons in the visual cortex have been identified. These neurons can be hierarchically...

Full description

Saved in:
Bibliographic Details
Published in:KI. Künstliche Intelligenz (Oldenbourg) Vol. 29; no. 1; pp. 19 - 29
Main Authors: Rodríguez-Sánchez, Antonio, Neumann, Heiko, Piater, Justus
Format: Magazine Article
Language:English
Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.02.2015
Subjects:
Artificial Intelligence
Computer Science
Discussion
Software Engineering/Programming and Operating Systems
Intermediate visual processing
Computer modeling
Boundary grouping
Shape representation
Feedback connections
junctions
ISSN:0933-1875, 1610-1987
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Knowledge of the brain has much advanced since the concept of the neuron doctrine developed by Ramón y Cajal (R Trim Histol Norm Patol 1:33–49, 1888 ). Over the last six decades a wide range of functionalities of neurons in the visual cortex have been identified. These neurons can be hierarchically organized into areas since neurons cluster according to structural properties and related function. The neurons in such areas can be characterized to a first order approximation by their (static) receptive field function, viz their filter characteristic implemented by their connection weights to neighboring cells. This paper aims to provide insights on the steps that computer models in our opinion must pursue in order to develop robust recognition mechanisms that mimic biological processing capabilities beyond the level of cells with classical simple and complex receptive field response properties. We stress the importance of intermediate-level representations to achieve higher-level object abstraction in the context of feature representations, and summarize two current approaches that we consider are advances toward achieving that goal.
ISSN:0933-1875
1610-1987
DOI:10.1007/s13218-014-0341-0