Principles of protein processing for a self-organising associative memory

Qadir, Omer; Liu, Jerry; Timmis, Jon; Tempesti, Gianluca; Tyrrell, Andy M.

doi:10.1109/cec.2010.5586419

Cited by 8 publications

(4 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fisher et al [1999] viewed proteins in signalling pathways as agents capable of rudimentary pattern recognition, memory, signal integration, etc. More recently, Qadir et al [2010] have used a protein metaphor to realize relatively faulttolerant associative memory in evolvable hardware. Most similar to the work presented here, and the only other known abstract model of genome and proteome interaction which may potentially be used as a general representation, is that by Knibbe et al [2008].…”

Section: Protein-inspired Computationmentioning

confidence: 99%

Production system rules as protein complexes from genetic regulatory networks: an initial study

Bull

2012

Evol. Intel.

View full text Add to dashboard Cite

This short paper introduces a new way by which to design production system rules. An indirect encoding scheme is presented which views such rules as protein complexes produced by the temporal behaviour of an artificial genetic regulatory network. This initial study begins by using a simple Boolean regulatory network to produce traditional ternary-encoded rules before moving to a fuzzy variant to produce real-valued rules.Competitive performance is shown with related genetic regulatory networks and rule-based systems on benchmark problems.

show abstract

Section: Protein-inspired Computationmentioning

confidence: 99%

Production system rules as protein complexes from genetic regulatory networks: an initial study

Bull

2012

Evol. Intel.

View full text Add to dashboard Cite

show abstract

“…The objective was to determine whether any meaningful computation could be achieved purely through memory operations and without performing any arithmetic operations at all. Although the architecture proposed in Qadir et al (2010) successfully navigated a robot in an environment with obstacles, it had issues for a hardware implementation. Creating a hardware implementable version is essential because implementing it on the traditional architecture voids the entire effort.…”

Section: Introductionmentioning

confidence: 97%

“…Traversing all these layers is a severe handicap for an application that intends to operate in real-time. In Qadir et al (2010) we proposed a novel architecture that uses hetero-associative recall to achieve artificial intelligence and explores the effect of moving computation into memory. The objective was to determine whether any meaningful computation could be achieved purely through memory operations and without performing any arithmetic operations at all.…”

Section: Introductionmentioning

confidence: 99%

Hardware architecture for a bidirectional hetero-associative Protein Processing Associative Memory

Qadir

Liu

Timmis

et al. 2011

2011 IEEE Congress of Evolutionary Computation (CEC)

Self Cite

View full text Add to dashboard Cite

This paper details an extension to an architecture for robust bidirectional hetero-associative recall. Our proposed Protein Processor Associative Memory (PPAM) is fundamentally different from the traditional processing methods which use arithmetic operations and consequently Arithmetic and Logic Units (ALUs). In this paper, we improve on our initial work addressing concerns surrounding hardware implementation. We present the improved computational architecture, coupled with a corresponding hardware architecture for implementation. Results of applying the hardware implementation on a small dataset are included, along with reports from synthesis tools about hardware utilisation.

show abstract

“…Arya et al [15] recognized human faces using Parallel Associative Memory. Qadir et al [16] [17] constructed and evaluated the performance of associative memories when they are used as a controller of a robot where sensory inputs contain errors. Wen et al [18] established memristive neural network based on the knowledge of memristor and recurrent neural network and applied for adaptive lag synchronization.…”

Section: Introductionmentioning

confidence: 99%

Restricted Boltzmann machine associative memory

Nagatani

Hagiwara

2014

2014 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

Restricted Boltzmann machine associative memory (RBMAM) is proposed in this paper. RBMAM memorizes patterns using contrastive divergence learning procedure. It recalls by calculating the reconstruction of pattern using conditional probability. In order to examine the performance of the proposed RBMAM, extensive computer simulations have been carried out. As the result, it has shown that the performance of RBMAM is overwhelming compared with the conventional neural network associative memories. For example as for storage capacity, RBMAM can store about from 2N hidden to 4N hideen patterns, where N hidden denotes the number of neurons in the hidden layer. Similarly we have obtained superior performance of RBMAM in respect of noise tolerance and pattern complement.

show abstract

Principles of protein processing for a self-organising associative memory

Cited by 8 publications

References 25 publications

Production system rules as protein complexes from genetic regulatory networks: an initial study

Production system rules as protein complexes from genetic regulatory networks: an initial study

Hardware architecture for a bidirectional hetero-associative Protein Processing Associative Memory

Restricted Boltzmann machine associative memory

Contact Info

Product

Resources

About