A massively parallel architecture for a self-organizing neural pattern recognition machine

Carpenter, Gail A.; Grossberg, Stephen

doi:10.1016/s0734-189x(87)80014-2

Cited by 2,260 publications

(576 citation statements)

References 18 publications

Supporting

Mentioning

545

Contrasting

Unclassified

Order By: Relevance

“…The F 2 equations derive from a Hodgkin-Huxley formulation with center-on, surround-off, connectivity [22]. Following the convention of [22], we use the index i to refer to the F 1 nodes and j to refer to the F 2 nodes.…”

Section: A Short-term Memory (Stm) Equationsmentioning

confidence: 99%

“…Following the convention of [22], we use the index i to refer to the F 1 nodes and j to refer to the F 2 nodes. We take A = 1, B = 0 and C > 0 [25], [26].…”

Section: A Short-term Memory (Stm) Equationsmentioning

confidence: 99%

“…However, the network in the reduced state is quite powerful, and is amenable to analytic treatment [25], [26]. Other algorithms have been proposed for cluster analysis of neural spike trains [22], [23], including the recently emphasized methods for the identification of spiking patterns within neural spike trains based on the Kmeans algorithm [17], [18]. Since all these methods require that data cluster on all of the dimensions, they suffer the dimensionality curse as the dimensions become larger.…”

Section: Application To Invertebrate Neuronsmentioning

confidence: 99%

“…One well-studied approach for clustering data without supervision is to use a neural network with Adaptive Resonance Theory (ART) [22], [23] (Figure 1a). ART neural networks have been shown to be very effective in self-organized data clustering problems when data cluster on all of the input dimensions.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Clustering neural spike trains with transient responses

Hunter¹,

Wu²,

Milton

2008

2008 47th IEEE Conference on Decision and Control

View full text Add to dashboard Cite

Abstract-The detection of transient responses, i.e. nonstationarities, that arise in a varying and small fraction of the total number of neural spike trains recorded from chronically implanted multielectrode grids becomes increasingly difficult as the number of electrodes grows. This paper presents a novel application of an unsupervised neural network for clustering neural spike trains with transient responses. This network is constructed by incorporating projective clustering into an adaptive resonance type neural network (ART) architecture resulting in a PART neural network. Since comparisons are made between inputs and learned patterns using only a subset of the total number of available dimensions, PART neural networks are ideally suited to the detection of transients. We show that PART neural networks are an effective tool for clustering neural spike trains that is easily implemented, computationally inexpensive, and well suited for detecting neural responses to dynamic environmental stimuli.

show abstract

Section: A Short-term Memory (Stm) Equationsmentioning

confidence: 99%

“…Following the convention of [22], we use the index i to refer to the F 1 nodes and j to refer to the F 2 nodes. We take A = 1, B = 0 and C > 0 [25], [26].…”

Section: A Short-term Memory (Stm) Equationsmentioning

confidence: 99%

Section: Application To Invertebrate Neuronsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Clustering neural spike trains with transient responses

Hunter¹,

Wu²,

Milton

2008

2008 47th IEEE Conference on Decision and Control

View full text Add to dashboard Cite

show abstract

“…Adaptive Resonance Theory (ART) is a class of ANN that is capable of self learning, ART1 type accepts binary inputs used primarily in pattern classification applications like text clustering (Carpenter and Grosberg, 1987), where documents are presented as binary strings characterizing the occurrences of features, including: taxonomy generation, topic extraction and search engines hits grouping, which are quite useful in many modern applications like hierarchical web search. Although the supervised Text Categorization (TC) is the best for such applications in terms of quality, it lacks adaptability, requires expert's intervention and occasional retraining (Fausett, 1993).…”

Section: Introductionmentioning

confidence: 99%

Adaptive Resonance Theory Training Parameters: Pretty Good Sets

Eldos¹

2010

Journal of Computer Science

View full text Add to dashboard Cite

Problem statement: ART1 artificial neural networks offer good tools for test clustering, where no expert is needed if the system is well trained. However, having no output reference for the input patterns makes it hard to judge the quality of the training. Moreover, the performance depends to a great extent on a set of training parameters. Designers follow some recommendations or depend on their expertise in finding good sets with no performance guarantees. Many methods were proposed; from greedy methods offering quick and acceptable solutions to evolutionary algorithms offering suboptimal sets of parameters. While the evolutionary algorithms are a good choice for quality, the computational cost is large even for an offline process; after all, computing resources are not for free. Approach: We introduced a method for selecting a set of parameters that yields a comparable performance and robust operation, with relatively low cost compared to the evolutionary methods. This method located a suitable set through repetitive portioning of the range, by considering the best subset for the next iteration. Results: Tests have shown that performance comparable with the computationally intensive evolutionary methods could be achieved in much less time. Conclusion: The repetitive portioning method for finding a good set of training parameters is very cost effective and yields good performance.

show abstract