"Herself´´s" AI - Insights

Agents, bots and spiders
Backpropagation networks
Evolutionary artificial intelligence
Game theory
Genetic algorithms
Hopfield networks
Neural networks
Particle swarms
Searches
Self organizing networks
Simulated annealing

A Revolution in Stochastic Optimization

The limitations of nonlinear optimization
is not due to non-linearity, but rather is
due to non-convexity.

- R. Horst, P. Pardalos, N. Thoai. Introduction to Global
Optimization. Kluwer, 1995.
- N. Karmarkar. A new polynomial-time algorithm for linear
programming. Combinatorica 4: 373–395, 1984.
- Y. Nesterov and A. Nemirovskii. Interior-Point
Polynomial Algorithms in Convex Programming. SIAM,
1994.
6. R. Fernholz. The Application of Stochastic Portfolio
Theory to Equity Management. INTECH research report,
2003.

Decision-support aids context-dependent autoassociative memory models.

Distributed associative memories are neural network models that fit perfectly well to the vision of cognition emerging from current neurosciences in the context-dependent autoassociative memory models for decision support systems.

REWIRING NEUROSCIENCE

REWIRING NEUROSCIENCE

Auto-associative Artificial Neural Memory

An auto-associative artificial neural memory is a system which stores mappings of specific input representations to specific output representations. That is to say, a system that "associates" two patterns such that when one is encountered subsequently, the other can be reliably recalled. Kohonen draws an analogy between associative memory and an adaptive filter function [2]. The filter can be viewed as taking an ordered set of input signals, and transforming them into another set of signals---the output of the filter. It is the notion of adaptation, allowing its internal structure to be altered by the transmitted signals, which introduces the concept of memory to the system.
A further refinement in terminology is possible with regard to the associative memory concept, and is ubiquitous in connectionist (neural network) literature in particular. A memory that reproduces its input pattern as output is referred to as autoassociative (i.e. associating patterns with themselves). One that produces output patterns dissimilar to its inputs is termed heteroassociative (i.e. associating patterns with other patterns).
Most associative memory implementations are realized as connectionist networks. Hopfield's collective computation network [1] serves as an excellent example of an autoassociative memory, whereas Rosenblatt's perceptron [3] is often utilized as a heteroassociator. There are many practical problems implementing effective associative memories however, most notably their inefficiency; the tendency is for them to fill up and become unreliable rather quickly. This is a long running open problem for both connectionism and adaptive filter theory---one that Kohonen refers to as the "problem of infinite state memory" [2].
References:
(1) J.J. Hopfield. Neural networks and physical systems with emergent collective computation abilities. Proceedings of the National Academy of Science. 79:2554-2558, 1982.
(2) T. Kohonen. Self-Organization and Associative Memory. Springer Series In Information Sciences, Vol.8. Springer-Verlag, Berlin, Heidelberg, New York, Tokyo, 1984.
(3) F. Rosenblatt. Principles of Neurodynamics. Spartan, New York, 1962.

Hybrid Artificial Neural Networks - Pattern Recognition

Pattern recognition includes a wide range of information processing problems, Research directions in our present interest:

Associative cognition systems with hybrid artificial neural networks for adaptive pattern recognition and interactive behavioristic relevance ranking classifiers

• speech recognition; speaker identification
• audio-visual pattern recognition (lip reading)
• optical character recognition of mathematical formulas"

Towards Integrated Nano-Associative Informatics Solutions

The human body is an extremely intelligent and complex adaptive system with a length scale on the order of a meter. The DNA/RNA and proteins molecules, which drive its natural processes possess dimensions on the nanometer range. The rapid development of nanotechnology has driven the production of molecular-scale devices towards the functionalizing of materials, directly manipulating of genetic molecules and engineering strains of proteins to possess novel functionalities. These basic processes that occur at the molecular level have opened up a world where leads us towards a compelling approach by fusing biotechnology, nanotechnology, and information science. This approach will enrich the development of revolutionary application-specific technologies.