WorldCat Identities

Ramacher, Ulrich 1949-

Overview
Works: 18 works in 60 publications in 3 languages and 1,054 library holdings
Roles: Author, Editor, Other, Collector, htt
Publication Timeline
.
Most widely held works by Ulrich Ramacher
On the construction of artificial brains by Ulrich Ramacher( )

16 editions published in 2010 in English and German and held by 474 WorldCat member libraries worldwide

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 this book we can present only a first generation artificial brain and believe many more generations will have to follow to reach the full power of the human brain, we nevertheless see a new era of computation on the horizon. There were times when computers, with their precision, reliability and blinding speed, were considered to be as superior to the wet matter of our brain as a jet plane is to a sparrow. These times seem to be over, given the fact that digital systems inspired by formal logic and controlled algorithmically - today's computers - are hitting a complexity crisis. A paradigm change is in the air: from the externally organised to the self-organised computer, of which the results described in this book may give an inkling
VLSI design of neural networks by Ulrich Ramacher( Book )

14 editions published between 1990 and 2012 in English and German and held by 286 WorldCat member libraries worldwide

The early era of neural network hardware design (starting at 1985) was mainly technology driven. Designers used almost exclusively analog signal processing concepts for the recall mode. Learning was deemed not to cause a problem because the number of implementable synapses was still so low that the determination of weights and thresholds could be left to conventional computers. Instead, designers tried to directly map neural parallelity into hardware. The architectural concepts were accordingly simple and produced the so­ called interconnection problem which, in turn, made many engineers believe it could be solved by optical implementation in adequate fashion only. Furthermore, the inherent fault-tolerance and limited computation accuracy of neural networks were claimed to justify that little effort is to be spend on careful design, but most effort be put on technology issues. As a result, it was almost impossible to predict whether an electronic neural network would function in the way it was simulated to do. This limited the use of the first neuro-chips for further experimentation, not to mention that real-world applications called for much more synapses than could be implemented on a single chip at that time. Meanwhile matters have matured. It is recognized that isolated definition of the effort of analog multiplication, for instance, would be just as inappropriate on the part ofthe chip designer as determination of the weights by simulation, without allowing for the computing accuracy that can be achieved, on the part of the user
Zur Konstruktion künstlicher Gehirne by Ulrich Ramacher( )

5 editions published in 2009 in German and English and held by 193 WorldCat member libraries worldwide

In diesem Buch wird eine erste Generation von künstlichen Hirnen für das Sehen vorgestellt. Auf der ausschlie"slichen Grundlage von Neuron- und Synapsenmodellen wird ein Objekterkennungssystem konstruiert, welches eine Merkmalspyramide mit 8 Orientierungen und 5 Auflösungsskalen für 1000 Objekte sowie die Netze für die Bindung von Merkmalen zu Objekten umfasst. Dieses Sehsystem kann unabhängig von der Beleuchtung, dem Gesichtausdruck, der Entfernung und einer Drehung, welche die Objektkomponenten sichtbar lä"st, Objekte erkennen. Seine Realisierung erfordert 59 Chips - davon sind 4 verschieden - welche mittels 3D Technologie zu einem Quader von 8mm x 8mm x 1mm aufgeschichtet sind. Die Leistungsfähigkeit des neuronal-synaptischen Netzwerkes beruht auf der Einführung von schnell veränderlichen dynamischen Synapsen. Anders als Netze mit konstanten Synapsen können solche mit dynamischen Synapsen allgemeine Aufgaben der Mustererkennung übernehmen. Die raum-zeitliche Korrelationsstruktur von Mustern wird durch eine einzige synaptische Differentialgleichung in universeller Weise erfasst. Die Korrelation kann in Erscheinung treten als synchrone Pulstätigkeit einer Neurongruppe, wodurch das Vorliegen eines Merkmals in robuster Weise angezeigt wird, oder als Bindung von Merkmalen zu Objekten. Auch wenn die Autoren der Überzeugung sind, dass noch viele Generationen folgen müssen, um die Leistungsfähigkeit des menschlichen Gehirns zu erreichen, sehen sie doch ein neues Rechen-Zeitalter aufziehen. Es gab Zeiten, da wurden Computer mit ihrer Präzision, Zuverlässigkeit und rasanten Geschwindigkeit der feuchten Materie unseres Gehirns als so weit überlegen angesehen wie das Düsenflugzeug dem Spatzen. Da"s diese Zeiten vorbei sind, ist gewi"s, denn durch formale Logik inspirierte, algorithmisch gesteuerte und mit digitaler Elektronik realisierte Systeme, die heutigen Computer, sto"sen an ihre Komplexitätsgrenzen. Andererseits eröffnen die hier vorge
Faddeev-Gleichungen in der funktionalen Quantentheorie des nicht-linearen Spinorfeldes by Ulrich Ramacher( Book )

4 editions published in 1979 in German and held by 30 WorldCat member libraries worldwide

Microelectronics for artificial neural nets( Book )

1 edition published in 1989 in English and held by 14 WorldCat member libraries worldwide

MxMobile : Abschlussbericht ; 01. März 2006 bis 30. Juni 2009( )

2 editions published in 2010 in German and held by 13 WorldCat member libraries worldwide

VLSI design of neural networks( Book )

2 editions published in 1991 in English and held by 11 WorldCat member libraries worldwide

VLSI Design of Neural Networks( )

in English and held by 8 WorldCat member libraries worldwide

Proceedings of the 2nd International Conference on Microelectronics for Neural Networks : October 16-18, 1991, Technical University of Munich, Munich, F.R. Germany by International Conference on Microelectronics for Neural Networks( Book )

4 editions published in 1991 in English and held by 5 WorldCat member libraries worldwide

SYNAPSE-1 : a high-speed general purpose parallel neurocomputer system by Joachim K Anlauf( )

1 edition published in 1995 in English and held by 2 WorldCat member libraries worldwide

Proceedings of the 1st International Workshop on Microelectronics for Neural Networks : June 25-26, 1990, University of Dortmund ... by 1990, Dortmund) International Workshop on Microelectronics for Neural Networks (1( Book )

2 editions published in 1990 in English and held by 2 WorldCat member libraries worldwide

A general-purpose signal processor architecture for neurocomputing and preprocessing applications by Ulrich Ramacher( )

1 edition published in 1993 in English and held by 2 WorldCat member libraries worldwide

Los neurocomputadores : una nueva clase de computadores by Ulrich Ramacher( )

1 edition published in 1994 in Spanish and held by 1 WorldCat member library worldwide

VLSI design of neural networks : [Workshop on Microelectronics ... Dortmund ... 1990]( Book )

1 edition published in 1991 in English and held by 1 WorldCat member library worldwide

On the Construction of Artificial Brains( )

1 edition published in 2010 in English and held by 0 WorldCat member libraries worldwide

Zur Konstruktion künstlicher Gehirne (German Edition)( Book )

1 edition published in 2009 in German and held by 0 WorldCat member libraries worldwide

Intelligent vision sensor for automotive applications by Axel Techmer( )

1 edition published in 2002 in English and held by 0 WorldCat member libraries worldwide

 
moreShow More Titles
fewerShow Fewer Titles
Audience Level
0
Audience Level
1
  General Special  
Audience level: 0.65 (from 0.52 for On the con ... to 1.00 for VLSI desig ...)

Zur Konstruktion künstlicher Gehirne
Covers
VLSI design of neural networksZur Konstruktion künstlicher Gehirne
Languages
English (44)

German (15)

Spanish (1)