CALM networks: a modular approach to supervised and unsupervised learning

Murre,; Phaf,; Wolters,

doi:10.1109/ijcnn.1989.118647

Cited by 20 publications

(7 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…An advantage of this approach is that it keeps the number of model elements low, and if these elements are "biological informed," a function that emerges in the model may possibly emerge in a similar manner in the brain. This particular approach builds on earlier work exploring the relationship between structure and function in neural network models (Murre et al, 1989(Murre et al, , 1992Murre, 1992;Happel and Murre, 1994).…”

Section: Certain Temporal Lobe Lesions That Have Recently Beenmentioning

confidence: 98%

TraceLink: A model of amnesia and consolidation of memory

Murre

1996

Hippocampus

105

View full text Add to dashboard Cite

Section: Certain Temporal Lobe Lesions That Have Recently Beenmentioning

confidence: 98%

TraceLink: A model of amnesia and consolidation of memory

Murre

1996

Hippocampus

105

View full text Add to dashboard Cite

“…The scheme of the relationship between attention and learning presented above seems particularly well suited for implementation in the connectionist framework and has, in fact, led to a new competitive learning procedure (Murre, Phaf, & Wolters, 1989;. This procedure has been used to build models for implicit and explicit memory tasks and for the role of novelty-based attention therein (e.g., Phaf, Postma, & Wolters, 1990).…”

mentioning

confidence: 99%

Attentional Shifts in Maintenance Rehearsal

Phaf¹,

Wolters²

1993

The American Journal of Psychology

View full text Add to dashboard Cite

“…However, there is another very important and crucial characteristic, the modular capacity. Murre et al [32], [33] point out that there is an abundance of evidence supporting modularity as an organizing principle in the brain, and that modular neural networks are not only most realistic from the implementation point of view, but that they may also be favored from a biological perspective [34]- [38]. This issue has been considered by several researchers [4], [5], [9]- [11].…”

Section: Introductionmentioning

confidence: 97%

A parallel processing VLSI BAM engine

Hasan

Siong

1997

IEEE Trans. Neural Netw.

View full text Add to dashboard Cite

In this paper emerging parallel/distributed architectures are explored for the digital VLSI implementation of adaptive bidirectional associative memory (BAM) neural network. A single instruction stream many data stream (SIMD)-based parallel processing architecture, is developed for the adaptive BAM neural network, taking advantage of the inherent parallelism in BAM. This novel neural processor architecture is named the sliding feeder BAM array processor (SLiFBAM). The SLiFBAM processor can be viewed as a two-stroke neural processing engine, It has four operating modes: learn pattern, evaluate pattern, read weight, and write weight. Design of a SLiFBAM VLSI processor chip is also described. By using 2-mum scalable CMOS technology, a SLiFBAM processor chip with 4+4 neurons and eight modules of 256x5 bit local weight-storage SRAM, was integrated on a 6.9x7.4 mm(2) prototype die. The system architecture is highly flexible and modular, enabling the construction of larger BAM networks of up to 252 neurons using multiple SLiFBAM chips.

show abstract

CALM networks: a modular approach to supervised and unsupervised learning

Cited by 20 publications

References 9 publications

TraceLink: A model of amnesia and consolidation of memory

TraceLink: A model of amnesia and consolidation of memory

Attentional Shifts in Maintenance Rehearsal

A parallel processing VLSI BAM engine

Contact Info

Product

Resources

About