Computational Investigation of Hemispheric Specialization and Interactions

Reggia, James A.; Shkuro, Yuri; Shevtsova, Natalia A.

doi:10.1007/3-540-44597-8_5

Cited by 5 publications

(3 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Step [56] and [63], the brain is a distributed neural network in diverse regions that perform processing in a parallel fashion.…”

Section: *D Is the Discriminant Functionmentioning

confidence: 99%

“…The brain carries out the cognitive processing by splitting the task into smaller sub tasks [106] so that the original complex task is no longer difficult to handle. The cerebral cortex being the biggest part of the brain, it could not work properly without regional modularity [56]. Regional modularity is the division of the cognitive task to different hemispheres of the brain.…”

Section: *D Is the Discriminant Functionmentioning

confidence: 99%

See 1 more Smart Citation

Hierarchical clustering using K-Iterations Fast Learning Artificial Neural Networks (KFLANN)

Wong¹

View full text Add to dashboard Cite

This thesis focuses on resolving the issues in high dimensional learning for neural networks. The curse of dimensionality has limited the growth of artificial neural network applications. While the curse is evident in current artificial systems, the stability and plasticity of the human biological brain shows no sign of this problem. Much of the information processing within the Prefrontal Cortex is performed as semantically transformed information. The work represented here, is broken into 4 stages. At the basic strata, an attempt is made to define an original stable platform, The K-iterations Fast Learning Artificial Neural Network (KFLANN), by which hierarchical systems can be built. Effort was spent in defining such a platform that provides a consistent clustering behavior, regardless the Data Presentation Sequence (DPS). The second stage of the work presents an original attempt to fuse the KFLANN with an approximation system by combining it with the Canonical Correlation Analysis (CCA). This is similar to the PCA, except that there is now a consideration of multiple dimensions. The resultant system is a hierarchical system which was called the HieFLANN. The third stage presents a second model of hierarchical nature, but differs from the HieFLANN in concept. The resultant HieFLANN_BP model represents an attempt to cascade atomized network models to process segments of the original problem, only to recombine processed information at varying hierarchical layers.

show abstract

“…Step [56] and [63], the brain is a distributed neural network in diverse regions that perform processing in a parallel fashion.…”

Section: *D Is the Discriminant Functionmentioning

confidence: 99%

Section: *D Is the Discriminant Functionmentioning

confidence: 99%

Hierarchical clustering using K-Iterations Fast Learning Artificial Neural Networks (KFLANN)

Wong¹

View full text Add to dashboard Cite

show abstract

“…Regional distributed modularity in the brain is based on various distributed neural networks in diverse regions which carry out processing in a parallel distributed manner to perform specific cognitive functions [11]. The brain performs as a group of collaborating networks, none of which can deal with a complex task alone.…”

Section: Introductionmentioning

confidence: 99%

A neurocognitive approach to self-organisation of verb actions

Elshaw

Wermter

Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290)

View full text Add to dashboard Cite

-Our approach integrates some neuroscience evidence for regional distributed modularity with cognitive evidence for action verb processing. The long-term goal is to provide a computational model for a neurally inspired selforganising robot action control system. Regional modularity in the brain involves distributed neural networks in diverse regions processing in a parallel manner. According to neurocognitive findings, action verbs are processed by associating specific cell assemblies with the appropriate body part. We present a model of the neurocognitive findings using self-organising networks that cluster action verbs into different locations of the network dependent on the body part they are associated with.

show abstract