Machine intelligence using hierarchical memory networks

This chapter presents the fundamentals of a hardware based memory network that can perform complex cognitive tasks. The network is designed to provide space dimensionality reduction, which enables desired functionality in a random environment. Complex network functionality is achieved by simple network cells that minimize the needed chip area for hardware implementation. Functionality of this network is demonstrated by automatic character recognition with various input deformations. In the character recognition, the network is trained to recognize characters deformed by random noise, rotation, scaling, and shifting. This example demonstrates how cognitive functionality of a hardware network can be achieved through an evolutionary process, as distinct from design based on mathematical formalism. DOI: 10.4018/978-1-4666-2518-1.ch003

[1]  David D. Nolte.  Mind at Light Speed: A New Kind of Intelligence , 2001 .

[2]  Bidyut B. Chaudhuri.  Digital Document Processing , 2007 .

[3]  Alan A. Stocker,et al.  Analog VLSI Circuits for the Perception of Visual Motion , 2006 .

[4]  Sina Balkir,et al.  Analog VLSI Design Automation , 2003 .

[5]  J. Hopfield,et al.  Computing with neural circuits: a model. , 1986, Science.

[6]  Vincenzo Catania,et al.  VLSI hardware architecture for complex fuzzy systems , 1999, IEEE Trans. Fuzzy Syst..

[7]  Kazuhisa Watanabe,et al.  A New Backpropagation Learning Algorithm for Layered Neural Networks with Nondifferentiable Units , 2007, Neural Computation.

[8]  Amit Konar,et al.  Artificial Intelligence and Soft Computing: Behavioral and Cognitive Modeling of the Human Brain , 1999 .

[9]  Evangelia Micheli-Tzanakou,et al.  Supervised and unsupervised pattern recognition: feature extraction and computational intelligence , 2000 .

[10]  Alex Pappachen James,et al.  Cognitive Memory Network , 2012, ArXiv.

[11]  I K Fodor,et al.  A Survey of Dimension Reduction Techniques , 2002 .

[12]  Yannis P. Tsividis,et al.  Mixed analog-digital fuzzy logic controller with continuous-amplitude fuzzy inferences and defuzzification , 1998, IEEE Trans. Fuzzy Syst..

[13]  Siegfried Engelmann,et al.  Inferred Functions of Performance and Learning , 2003 .

[14]  W. Robertson,et al.  An hierarchical VLSI neural network architecture , 1992 .

[15]  Nick Chater.  Cognitive science: The logic of human learning , 2000, Nature.

[16]  Dov M. Gabbay,et al.  Handbook of logic in artificial intelligence and logic programming (vol. 1) , 1993 .

[17]  Sankar K. Pal,et al.  Pattern Recognition: From Classical to Modern Approaches , 2001 .

[18]  Maurizio Valle,et al.  Analog VLSI Implementation of Artificial Neural Networks with Supervised On-Chip Learning , 2002 .

[19]  J.J. Hopfield,et al.  Artificial neural networks , 1988, IEEE Circuits and Devices Magazine.