000			036940000a22003370004500
003			EG-GICUC
005			20250223030655.0
008			060917s2006 ua a f m 000 0 eng d
040			_aEG-GICUC _beng _cEG-GICUC
041	0		_aEng
049			_aDeposite
097			_aM.Sc
099			_aCai01.13.03.M.Sc.2006.Ka.N.
100	0		_aKarim Ahmed Youssry Mohamed ElLaithy
245	1	2	_aA Novel Representation of Artificial Neural Netwoks with Dynamic Synapses / _cKarim Ahmed Youssry Mohamed ElLaithy ; Supervised Bassel Tawfeek , Mohamed Saad El Shereif , Magda Fayek
246	1	5	_aاسلوب جديد للتعبير عن الشبكات العصبية الصناعية المزودة بالوصلات العصبية الديناميكية
260			_aCairo : _bKarim Ahmed Youssry Mohamed ElLaithy , _c2006
300			_a97P : _bill ; _c30cm
502			_aThesis (M.Sc.) - Cairo University - Faculty Of Engineering - Department Of Biomedical Engineering
520			_aArtificial Neural Networks (ANN) has proved to be a useful tool for information processingThe problem with conventional ANN is that it assumes that the synapses are staticIn human nervous system , however , synapses are dynamicThese dynamics arise from the influence of pre - synaptic mechanisms on the release from an axon terminalThese mechanisms are facilitation and pre - synaptic feedback inhibition which are fundamental features of biological neuronsConsequently , the probability of release becomes a function of the temporal pattern of action potential occurrenceHence , the strength of a given synapse varies upon the arrival of each action potential invading the terminal regionWe developed an implementation for a stochastic model as computational tool for pattern recognitionWe use the computational capacity of the dynamic synapses for transforming the temporal pattern of spikes into a spatial - temporal pattern of synaptic eventsIn this implementation , the system is learned to extract a short statistically significant sub - pattern in the spike trainSuch a capability for extracting invariant temporal features allows the transmission of information contained within noisy and variable spike trainsThe computational performance is evaluated qualitatively and quantitatively in comparison with the traditional artificial neural networks and a basic version of the stochastic modelAfter training , the network generates high correlated signals when the input signals are similar in there temporal and statistical featuresThe network is tested also for different temporal but same statistical features in input signalsAnother configuration is used for speech signal recognitionThe speech recognition was to differ between two spoken words without any control on the ambient noiseThe results are ensuring that despite how small is the network , the performance is higher than another approach utilizing the same concept of dynamic synapses but in different integrationThe results ensure the enhanced performance of the proposed approach over the other mentioned techniquesMoreover , the embedded encoding within the neural configurations is analyzed by the relative entropy , Kullback - Leibler distanceThis measurement ensured that the network is dealing with the different input signals with statistically dependant manner
530			_aIssued also as CD
653		4	_aArtificial Neural Netwroks
653		4	_aSynapses
700	0		_aBassel Tawfeek , _eSupervisor
700	0		_aMagda Fayek , _eSupervisor
700	0		_aMohamed Saad El Shereif , _eSupervisor
856			_uhttp://172.23.153.220/th.pdf
905			_aAmira _eCataloger
905			_aMustafa _eRevisor
942			_2ddc _cTH
999			_c39555 _d39555