A novel Episodic Associative Memory model for enhanced classification accuracy

Wickramasinghe, Leelani Kumari; Alahakoon, L.D.; Smith‐Miles, Kate

doi:10.1016/j.patrec.2007.02.012

Cited by 8 publications

(6 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Synapses in real neurons tend to exhaust their resources, i.e., their strength decreases when used. If we consider the dynamic synapses [13,36], the synaptic weight discussed above, w ij evolves within time t as follows [30] w…”

Section: Associative Memory With Nonlinear Function Constitution and mentioning

confidence: 99%

“…The patterns can be stored in the network by setting of synaptic weight, but a big number of spurious states exist in the traditional Hopfield networks [20]. According to the Hebbian learning rule [36], the synaptic weight matrix is static, and therefore the neuron's local field is linear with the state of the neuron. There is no depression for the neuron's local field.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Anti-Spurious-State Neural Network Using Nonlinear Outer Product and Dynamic Synapses

Xia¹,

Shen²,

Wang³

et al. 2016

NNW

View full text Add to dashboard Cite

Precise wind energy potential assessment is vital for wind energy generation and planning and development of new wind power plants. This work proposes and evaluates a novel two-stage method for location-specific wind energy potential assessment. It combines accurate statistical modelling of annual wind direction distribution in a given location with supervised machine learning of efficient estimators that can approximate energy efficiency coefficients from the parameters of optimized statistical wind direction models. The statistical models are optimized using differential evolution and energy efficiency is approximated by evolutionary fuzzy rules.

show abstract

Section: Associative Memory With Nonlinear Function Constitution and mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Anti-Spurious-State Neural Network Using Nonlinear Outer Product and Dynamic Synapses

Xia¹,

Shen²,

Wang³

et al. 2016

NNW

View full text Add to dashboard Cite

show abstract

“…In the real brain function, the stored patterns are always correlative with each other, but in many past neural network models of memory, including Winder's model, the hetero-association between the stored patterns is ignored. In most traditional memory models, the stored memories would typically tend to be in fixed point attractor states [28][29][30], which cannot realize the sequence memory. The hetero-association between the stored patterns is crucial in the memory information processing, and is always regarded as a mechanism with an ability to get out of stable state in a neural network [31,32].…”

Section: Introductionmentioning

confidence: 99%

Sequence memory based on an oscillatory neural network

Xia

Weng

Wang

et al. 2014

Sci. China Inf. Sci.

View full text Add to dashboard Cite

A recurrent neural network based on memristive activation function and its associative memory SCIENTIA SINICA Informationis 47, 1226 (2017); A memory model for image recognition and classification based on convolutional neural network and Bayesian decision SCIENTIA SINICA Technologica 47, 977 (2017); Fold-Hopf bifurcation in a simplified four-neuron BAM (bidirectional associative memory) neural network with two delays SCIENCE CHINA Technological Sciences 53, 633 (2010); Medical image segmentation based on cellular neural network Science in China Series F-Information Sciences 44, 68 (2001);. RESEARCH PAPER. SCIENCE CHINA Information Sciences

show abstract

“…Other schemes of associative memories based on recurrent neural networks, see for example [12,13], and other techniques [14][15][16][17][18] have been proposed.…”

Section: Introductionmentioning

confidence: 99%

A New Associative Model with Dynamical Synapses

Monteros¹,

Azuela²

2008

Neural Process Lett

View full text Add to dashboard Cite

The brain is not a huge fixed neural network, but a dynamic, changing neural network that continuously adapts to meet the demands of communication and computational needs. In classical neural networks approaches, particularly associative memory models, synapses are only adjusted during the training phase. After this phase, synapses are no longer adjusted. In this paper we describe a new dynamical model where synapses of the associative memory could be adjusted even after the training phase as a response to an input stimulus. We provide some propositions that guarantee perfect and robust recall of the fundamental set of associations. In addition, we describe the behavior of the proposed associative model under noisy versions of the patterns. At last, we present some experiments aimed to show the accuracy of the proposed model.

show abstract

A novel Episodic Associative Memory model for enhanced classification accuracy

Cited by 8 publications

References 17 publications

Anti-Spurious-State Neural Network Using Nonlinear Outer Product and Dynamic Synapses

Anti-Spurious-State Neural Network Using Nonlinear Outer Product and Dynamic Synapses

Sequence memory based on an oscillatory neural network

A New Associative Model with Dynamical Synapses

Contact Info

Product

Resources

About