Oscillatory corticothalamic response to somatosensory input

Gelenbe, Erol; Cramer, Christopher

doi:10.1016/s0303-2647(98)00051-3

Cited by 26 publications

(19 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Random Neural Network (RNN) was developed to mimic the behaviour of biological neurons in the brain [1], [2] and its generalisations [3]. Applications of the RNN have focused on its recurrent structure and learning capabilities [4] especially in image processing [5], [6], as well as in recent work [7]- [12].…”

Section: Introductionmentioning

confidence: 99%

Single-cell based random neural network for deep learning

Yin

Gelenbe

2017

2017 International Joint Conference on Neural Networks (IJCNN)

Self Cite

View full text Add to dashboard Cite

Recent work demonstrated the value of multi clusters of spiking Random Neural Networks (RNN) with dense soma-to-soma interactions in deep learning. In this paper we go back to the original simpler structure and we investigate the power of single RNN cells for deep learning. First, we consider three approaches with the single cells, twin cells and multi-cell clusters. This first part shows that RNNs with only positive parameter can conduct convolution operations similar to those of the convolutional neural network. We then develop a multi-layer architecture of single cell RNNs (MLSRNN), and show that this architecture achieves comparable or better classification at lower computation cost than conventional deeplearning methods.

show abstract

Section: Introductionmentioning

confidence: 99%

Single-cell based random neural network for deep learning

Yin

Gelenbe

2017

2017 International Joint Conference on Neural Networks (IJCNN)

Self Cite

View full text Add to dashboard Cite

show abstract

“…5. Using the results from Steps 3 and 4, update the matrices W + = {w + (i, j)}, W − = {w − (i, j)} and A = {a(i, j)} using (15) and (16). If during some update a particular parameter does not satisfy the constraint that they must be non-negative, then either the particular update can be repeated with a smaller value of η or the particular parameter can be set to the closest values within the constraints.…”

Section: Steps Of the Algorithmmentioning

confidence: 99%

“…The application of the RNN to the approximate solution of optimisation problems was discussed in [9,14], while a similar model was suggested for the analysis of genetic algorithms [15]. An application of the RNN to the study of cortico-thalamic oscillations is discussed in [16]. The RNN has also been applied to the control of quality of service based routing for computer networks [21,26].…”

Section: Introductionmentioning

confidence: 99%

Synchronized Interactions in Spiked Neuronal Networks

Gelenbe

Timotheou

2008

The Computer Journal

View full text Add to dashboard Cite

The study of artificial neural networks has originally been inspired by neurophysiology and cognitive science. It has resulted in a rich and diverse methodology and in numerous applications to machine intelligence, computer vision, pattern recognition and other applications. The random neural network (RNN) is a probabilistic model which was inspired by the spiking behaviour of neurons, and which has an elegant mathematical treatment which provides both its steady-state behaviour and offers efficient learning algorithms for recurrent networks. Second order interactions, where more than one neuron jointly act upon other cells, have been observed in nature; they generalise the binary (excitatory-inhibitory) interaction between pairs of cells and give rise to synchronous firing by many cells. In this paper we develop an extension of the RNN to the case of synchronous interactions which are based on at two cells that jointly excite a third cell; this local behaviour is in fact sufficient to create synchronous firing by large ensembles of cells. We describe the system state and derive its stationary solution as well as a O(N 3) gradient descent learning algorithm for a recurrent network with N cells when both standard excitatory-inhibitory interactions, as well as synchronous firing, are present. * This research was undertaken as part of the ALADDIN (Autonomous Learning Agents for Decentralised Data and Information Systems) project and is jointly funded by a BAE Systems and EPSRC (UK Engineering and Physical Research Council) strategic partnership under Grant No. EP/C548051/1.

show abstract

“…The RNN has been used for modelling natural neuronal networks [ 21 ], and for protein alignment [ 22 ]. It has been used with its learning algorithm [ 18 ] in several image processing applications including learning colour textures [ 23 ], the accurate evaluation of tumours from brain MRI scans [ 24 ] and the compression of still and moving images [ 25 , 26 , 27 ].…”

Section: Introductionmentioning

confidence: 99%

G-Networks to Predict the Outcome of Sensing of Toxicity

Grenet¹,

Yin

Comet³

2018

Sensors

View full text Add to dashboard Cite

G-Networks and their simplified version known as the Random Neural Network have often been used to classify data. In this paper, we present a use of the Random Neural Network to the early detection of potential of toxicity chemical compounds through the prediction of their bioactivity from the compounds’ physico-chemical structure, and propose that it be automated using machine learning (ML) techniques. Specifically the Random Neural Network is shown to be an effective analytical tool to this effect, and the approach is illustrated and compared with several ML techniques.

show abstract

Oscillatory corticothalamic response to somatosensory input

Cited by 26 publications

References 8 publications

Single-cell based random neural network for deep learning

Single-cell based random neural network for deep learning

Synchronized Interactions in Spiked Neuronal Networks

G-Networks to Predict the Outcome of Sensing of Toxicity

Contact Info

Product

Resources

About