Syntactical Pattern Recognition
Statistical Pattern Recognition
Adaptive Data Structures
Artificial Neural Networks
Data Retrieval and Storage
Following are some of the major results obtained in the area
of Artificial Neural Networks.
- Have enhanced the Self-Organizing Map (SOM) by incorporating into it any arbitrary user-defined tree-based topology. The resulting neural network, the TTO-SOM, was presented as a plenary talk at CORES'09
(Proc. CORES 2009).
This result was further enhanced by including into it the concept of adaptively changing the structure of the tree
(Proc. AI 2009: This paper won the Best Paper Award of the Conference).
The entire theory of merging the fields of SOMs and adaptive data structures is based on the results of Astudillo and myself.
- Have shown how we can quantify Behavioral Synchronization in a network of Bursting neurons
(Proc. AI 2007).
- Have used large-scale chaotic neural models of the brain to study epilepsy (Proc. ICHSS 2008) and schizophrenia
(Proc. CCECE 2005).
- Have proposed how spikes can be annihilated in the Hodgkin-Huxley neuron
(J. Bio. Cyb. 2008, Proc. BVAI 2007, Proc. CanAI 2007).
- Have designed two Kohonen-like networks for the Map Reconstruction Problem
(Proc. EIS 2004).
- Have generalized the latter to yield a Neural Network which decomposes the data points, and individually computes the Hamiltonian paths for these decomposed subsets. It then merges these solutions to yield an overall solution for the Euclidian Travelling Salesman Problem (IEEE T:NN 2003).
- Have designed a Kohonen Network which Incorporates Explicit Statistics (KNIES). This network has been used to efficiently solve the Euclidian Travelling Salesman Problem and the Hamiltonian Path Problem
(NN 1999, Comp. and OR 2000).
- Have developed Kohonen-like discretized-space and continuous-space neural algorithms for distance function estimation. These algorithms have been used for estimating road distances in Turkey
(ORSA J. Comp. 1997, IEEE T:SMC 1998).