On the Construction of Artificial Brains. 1st ed. 2010

種類:

電子ブック

責任表示:

edited by Ulrich Ramacher, Christoph von der Malsburg

出版情報:

Berlin, Heidelberg : Springer Berlin Heidelberg : Imprint: Springer, 2010

著者名:

• Ramacher, Ulrich.
• von der Malsburg, Christoph.
• SpringerLink (Online service)

ISBN:

9783642001895 [3642001890]    

注記:

Prologue -- The Difficulty of Modelling Artificial Brains -- Information Processing in Nets with Constant Synapses -- Theory of Nets with Constant or Dynamic Synapses -- Macro-Dynamics of Nets with Constant Synapses -- Information Processing with Dynamic Synapses -- Nets for Feature Detection -- Nets for Feature Recognition -- Nets for Robust Head Detection -- Extensions of the Vision Architecture -- Look-out -- Preliminary Considerations on the Microelectronic Implementation -- Elementary Circuits for Neurons, Synapses, and Photosensors -- Simulation of Microelectronic Neural Circuits and Systems -- Architecture and Chip Design of the Feature Recognizer -- Architecture and Chip Design of the Feature Detector -- 3D Stacking Technology -- Architecture of First Generation Vision Cube -- End.
This book presents a first generation of artificial brains, using vision as sample application. An object recognition system is built, using neurons and synapses as exclusive building elements. The system contains a feature pyramid with 8 orientations and 5 resolution levels for 1000 objects and networks for binding of features into objects. This vision system can recognize objects robustly in the presence of changes in illumination, deformation, distance and pose (as long as object components remain visible). The neuro-synaptic network owes its functional power to the introduction of rapidly modifiable dynamic synapses. These give a network greater pattern recognition capabilities than are achievable with fixed connections. The spatio-temporal correlation structure of patterns is captured by a single synaptic differential equation in a universal way. The correlation can appear as synchronous neural firing, which signals the presence of a feature in a robust way, or binds features into objects. Although in th

ローカル注記:

学内専用E-BOOKS (local access only)