Search results for: multiplicative neuron

Authors: Kavita Burse, Manish Manoria, Vishnu P. S. Kirar

Abstract:

The back propagation algorithm calculates the weight changes of artificial neural networks, and a common approach is to use a training algorithm consisting of a learning rate and a momentum factor. The major drawbacks of above learning algorithm are the problems of local minima and slow convergence speeds. The addition of an extra term, called a proportional factor reduces the convergence of the back propagation algorithm. We have applied the three term back propagation to multiplicative neural network learning. The algorithm is tested on XOR and parity problem and compared with the standard back propagation training algorithm.

Keywords: Three term back propagation, multiplicative neuralnetwork, proportional factor, local minima.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2814

Authors: E. Ansari-Piri, N. Eghbali

Abstract:

Let A and B be two linear algebras. A linear map ϕ : A → B is called an n-homomorphism if ϕ(a1...an) = ϕ(a1)...ϕ(an) for all a1, ..., an ∈ A. In this note we have a verification on the behavior of almost n-multiplicative linear maps with n > 2 in the fuzzy normed spaces

Keywords: Almost multiplicative maps, n-homomorphism maps, almost n-multiplicative maps, fuzzy normed space, stability.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1280

Authors: Liu Ping

Abstract:

In this paper, for an arbitrary multiplicative functional f from the set of all upper triangular fuzzy matrices to the fuzzy algebra, we prove that there exist a multiplicative functional F and a functional G from the fuzzy algebra to the fuzzy algebra such that the image of an upper triangular fuzzy matrix under f can be represented as the product of all the images of its main diagonal elements under F and other elements under G.

Keywords: Multiplicative functional, triangular fuzzy matrix, fuzzy addition operation, fuzzy multiplication operation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1196

Authors: J. C. Moctezuma, V. Breña-Medina, Jose Luis Nunez-Yanez, Joseph P. McGeehan

Abstract:

In this work we make a bifurcation analysis for a single compartment representation of Traub model, one of the most important conductance-based models. The analysis focus in two principal parameters: current and leakage conductance. Study of stable and unstable solutions are explored; also Hop-bifurcation and frequency interpretation when current varies is examined. This study allows having control of neuron dynamics and neuron response when these parameters change. Analysis like this is particularly important for several applications such as: tuning parameters in learning process, neuron excitability tests, measure bursting properties of the neuron, etc. Finally, a hardware implementation results were developed to corroborate these results.

Keywords: Traub model, Pinsky-Rinzel model, Hopf bifurcation, single-compartment models, Bifurcation analysis, neuron modeling.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1205

Authors: Changjin Xu

Abstract:

In this paper, we consider a two-neuron system with time-delayed connections between neurons. By analyzing the associated characteristic transcendental equation, its linear stability is investigated and Hopf bifurcation is demonstrated. Some explicit formulae for determining the stability and the direction of the Hopf bifurcation periodic solutions bifurcating from Hopf bifurcations are obtained by using the normal form theory and center manifold theory. Some numerical simulation results are given to support the theoretical predictions. Finally, main conclusions are given.

Keywords: Two-neuron system, delay, stability, Hopf bifurcation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1324

Authors: Nishant Singh, Christian Huyck, Vaibhav Gandhi, Alexander Jones

Abstract:

A robotic arm and hand controlled by simulated neurons is presented. The robot makes use of a biological neuron simulator using a point neural model. The neurons and synapses are organised to create a finite state automaton including neural inputs from sensors, and outputs to effectors. The robot performs a simple pick-and-place task. This work is a proof of concept study for a longer term approach. It is hoped that further work will lead to more effective and flexible robots. As another benefit, it is hoped that further work will also lead to a better understanding of human and other animal neural processing, particularly for physical motion. This is a multidisciplinary approach combining cognitive neuroscience, robotics, and psychology.

Keywords: Robot, neuron, cell assembly, spiking neuron, force sensitive resistor.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1975

Authors: Amrita Tripathi, Neeru Adlakha

Abstract:

Calcium [Ca2+] dynamics is studied as a potential form of neuron excitability that can control many irregular processes like metabolism, secretion etc. Ca2+ ion enters presynaptic terminal and increases the synaptic strength and thus triggers the neurotransmitter release. The modeling and analysis of calcium dynamics in neuron cell becomes necessary for deeper understanding of the processes involved. A mathematical model has been developed for cylindrical shaped neuron cell by incorporating physiological parameters like buffer, diffusion coefficient, and association rate. Appropriate initial and boundary conditions have been framed. The closed form solution has been developed in terms of modified Bessel function. A computer program has been developed in MATLAB 7.11 for the whole approach.

Keywords: Laplace Transform, Modified Bessel function, reaction diffusion equation, diffusion coefficient, excess buffer, calcium influx

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1961

Authors: Sandeep Chandana, Rene V. Mayorga

Abstract:

The paper presents a new hybridization methodology involving Neural, Fuzzy and Rough Computing. A Rough Sets based approximation technique has been proposed based on a certain Neuro – Fuzzy architecture. A New Rough Neuron composition consisting of a combination of a Lower Bound neuron and a Boundary neuron has also been described. The conventional convergence of error in back propagation has been given away for a new framework based on 'Output Excitation Factor' and an inverse input transfer function. The paper also presents a brief comparison of performances, of the existing Rough Neural Networks and ANFIS architecture against the proposed methodology. It can be observed that the rough approximation based neuro-fuzzy architecture is superior to its counterparts.

Keywords: Boundary neuron, neuro-fuzzy, output excitation factor, RANFIS, rough approximation, rough neural computing.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1703

Authors: Kavita Burse, R.N. Yadav, S.C. Shrivastava, Vishnu Pratap Singh Kirar

Abstract:

During signal transmission, the combined effect of the transmitter filter, the transmission medium, and additive white Gaussian noise (AWGN) are included in the channel which distort and add noise to the signal. This causes the well defined signal constellation to spread causing errors in bit detection. A compact pi neural network with minimum number of nodes is proposed. The replacement of summation at each node by multiplication results in more powerful mapping. The resultant pi network is tested on six different channels.

Keywords: Additive white Gaussian noise, digitalcommunication system, multiplicative neuron, Pi neural network.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1667

Authors: Le Zhao, Alain Nogaret

Abstract:

We have built universal central pattern generator (CPG) hardware by interconnecting Hodgkin-Huxley neurons with reciprocally inhibitory synapses. We investigate the dynamics of neuron oscillations as a function of the time delay between current steps applied to individual neurons. We demonstrate stimulus dependent switching between spiking polyrhythms and map the phase portraits of the neuron oscillations to reveal the basins of attraction of the system. We experimentally study the dependence of the attraction basins on the network parameters: The neuron response time and the strength of inhibitory connections.

Keywords: Central pattern generator, winnerless competition principle.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1751

Authors: Anupama Pande, Ashok Kumar Thakur, Swapnoneel Roy

Abstract:

A complex valued neural network is a neural network which consists of complex valued input and/or weights and/or thresholds and/or activation functions. Complex-valued neural networks have been widening the scope of applications not only in electronics and informatics, but also in social systems. One of the most important applications of the complex valued neural network is in signal processing. In Neural networks, generalized mean neuron model (GMN) is often discussed and studied. The GMN includes a new aggregation function based on the concept of generalized mean of all the inputs to the neuron. This paper aims to present exhaustive results of using Generalized Mean Neuron model in a complex-valued neural network model that uses the back-propagation algorithm (called -Complex-BP-) for learning. Our experiments results demonstrate the effectiveness of a Generalized Mean Neuron Model in a complex plane for signal processing over a real valued neural network. We have studied and stated various observations like effect of learning rates, ranges of the initial weights randomly selected, error functions used and number of iterations for the convergence of error required on a Generalized Mean neural network model. Some inherent properties of this complex back propagation algorithm are also studied and discussed.

Keywords: Complex valued neural network, Generalized Meanneuron model, Signal processing.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1729

Authors: Yayun Hsu, Henry Horng-Shing Lu

Abstract:

This paper proposes a data-driven, biology-inspired neural segmentation method of 3D drosophila Brainbow images. We use Bayesian Sequential Partitioning algorithm for probabilistic modeling, which can be used to detect somas and to eliminate crosstalk effects. This work attempts to develop an automatic methodology for neuron image segmentation, which nowadays still lacks a complete solution due to the complexity of the image. The proposed method does not need any predetermined, risk-prone thresholds, since biological information is inherently included inside the image processing procedure. Therefore, it is less sensitive to variations in neuron morphology; meanwhile, its flexibility would be beneficial for tracing the intertwining structure of neurons.

Keywords: Brainbow, 3D imaging, image segmentation, neuron morphology, biological data mining, non-parametric learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2258

Authors: C. Ardil

Abstract:

Multiplicative multiple criteria decision making analysis (MCDMA) method is a systematic decision support system to aid decision makers reach appropriate decisions. The application of multiplicative MCDMA in the military aircraft selection problem is significant for proper decision making process, which is the decisive factor in minimizing expenditures and increasing defense capability and capacity. Nine military fighter aircraft alternatives were evaluated by ten decision criteria to solve the decision making problem. In this study, multiplicative MCDMA model aims to evaluate and select an appropriate military fighter aircraft for the Air Force fleet planning. The ranking results of multiplicative MCDMA model were compared with the ranking results of additive MCDMA, logarithmic MCDMA, and regrettive MCDMA models under the L₂ norm data normalization technique to substantiate the robustness of the proposed method. The final ranking results indicate the military fighter aircraft Su-57 as the best available solution.

Keywords: Aircraft Selection, Military Fighter Aircraft Selection, Air Force Fleet Planning, Multiplicative MCDMA, Additive MCDMA, Logarithmic MCDMA, Regrettive MCDMA, Mean Weight, Multiple Criteria Decision Making Analysis, Sensitivity Analysis

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 771

Authors: A. Muthuramalingam, S. Himavathi, E. Srinivasan

Abstract:

.Hardware realization of a Neural Network (NN), to a large extent depends on the efficient implementation of a single neuron. FPGA-based reconfigurable computing architectures are suitable for hardware implementation of neural networks. FPGA realization of ANNs with a large number of neurons is still a challenging task. This paper discusses the issues involved in implementation of a multi-input neuron with linear/nonlinear excitation functions using FPGA. Implementation method with resource/speed tradeoff is proposed to handle signed decimal numbers. The VHDL coding developed is tested using Xilinx XC V50hq240 Chip. To improve the speed of operation a lookup table method is used. The problems involved in using a lookup table (LUT) for a nonlinear function is discussed. The percentage saving in resource and the improvement in speed with an LUT for a neuron is reported. An attempt is also made to derive a generalized formula for a multi-input neuron that facilitates to estimate approximately the total resource requirement and speed achievable for a given multilayer neural network. This facilitates the designer to choose the FPGA capacity for a given application. Using the proposed method of implementation a neural network based application, namely, a Space vector modulator for a vector-controlled drive is presented

Keywords: FPGA implementation, multi-input neuron, neural network, nn based space vector modulator.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 4422

Authors: Nina Robson, Kenneth John Faller II, Vishalkumar Ahir, Arthur Ricardo Deps Miguel Ferreira, John Buchanan, Amarnath Banerjee

Abstract:

This paper describes the development of a virtual-reality system ARWED, which will be used in physical rehabilitation of patients with reduced upper extremity mobility to increase limb Active Range of Motion (AROM). The ARWED system performs a symmetric reflection and real-time mapping of the patient’s healthy limb on to their most affected limb, tapping into the mirror neuron system and facilitating the initial learning phase. Using the ARWED, future experiments will test the extension of the action-observation priming effect linked to the mirror-neuron system on healthy subjects and then stroke patients.

Keywords: Physical rehabilitation, mirror neuron, virtual reality, stroke therapy.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1950

Authors: R. Keerativittatayut, B. Kaewkamnerdpong, J. Laothamatas, W. Sungkarat

Abstract:

Dynamic Causal Modeling (DCM) functional Magnetic Resonance Imaging (fMRI) is a promising technique to study the connectivity among brain regions and effects of stimuli through modeling neuronal interactions from time-series neuroimaging. The aim of this study is to study characteristics of a mirror neuron system (MNS) in elderly group (age: 60-70 years old). Twenty volunteers were MRI scanned with visual stimuli to study a functional brain network. DCM was employed to determine the mechanism of mirror neuron effects. The results revealed major activated areas including precentral gyrus, inferior parietal lobule, inferior occipital gyrus, and supplementary motor area. When visual stimuli were presented, the feed-forward connectivity from visual area to conjunction area was increased and forwarded to motor area. Moreover, the connectivity from the conjunction areas to premotor area was also increased. Such findings can be useful for future diagnostic process for elderly with diseases such as Parkinson-s and Alzheimer-s.

Keywords: Mirror Neuron System (MNS), Dynamic Causal Modeling (DCM), Functional Magnetic Resonance Imaging (fMRI)

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1727

Authors: Isaac Cassar, Trevor Davis, Yi-Kai Lo, Wentai Liu

Abstract:

Retinal prostheses have been successful in eliciting visual responses in implanted subjects. As these prostheses progress, one of their major limitations is the need for increased resolution. As an alternative to increasing the number of electrodes, virtual electrodes may be used to increase the effective resolution of current electrode arrays. This paper presents a virtual electrode technique based upon time-offsets between stimuli. Two adjacent electrodes are stimulated with identical pulses with too short of pulse widths to activate a neuron, but one has a time offset of one pulse width. A virtual electrode of twice the pulse width was then shown to appear in the center, with a total width capable of activating a neuron. This can be used in retinal implants by stimulating electrodes with pulse widths short enough to not elicit responses in neurons, but with their combined pulse width adequate to activate a neuron in between them.

Keywords: Electrical stimulation, Neuroprosthesis, Retinal implant, Retinal Prosthesis, Virtual electrode.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1790

Authors: Kejun Zhuang, Zhaohui Wen

Abstract:

In this paper, a tri–neuron network model with time delay is investigated. By using the Bendixson-s criterion for high– dimensional ordinary differential equations and global Hopf bifurcation theory for functional differential equations, sufficient conditions for existence of periodic solutions when the time delay is sufficiently large are established.

Keywords: Delay, global Hopf bifurcation, neural network, periodicsolutions.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1482

Authors: Zhengkun Guo, Yanbin Li, Wenqing Wang, Bo Zou

Abstract:

Active radar and sonar systems often report Doppler measurements in addition to the position measurements such as range and bearing. The tracker can perform better by making full use of the Doppler measurements. However, due to the high nonlinearity of the Doppler measurements with respect to the target state in the Cartesian coordinate systems, those measurements are not always fully exploited. This paper mainly focuses on dealing with the Doppler measurements as well as the position measurements in Polar coordinates. The Statically Fused Converted Position and Doppler Measurements Kalman Filter (SF-CMKF) with additive debiased measurement conversion has been presented. However, the exact compensation for the bias of the measurement conversion are multiplicative and depend on the statistics of the cosine of the angle measurement errors. As a result, the consistency and performance of the SF-CMKF may be suboptimal in the large angle error situations. In this paper, the multiplicative unbiased position and Doppler measurement conversion for two-dimensional (Polar-to-Cartesian) tracking are derived, and the SF-CMKF is improved by using those conversion. Monte Carlo simulations are presented to demonstrate the statistic consistency of the multiplicative unbiased conversion and the superior performance of the modified SF-CMKF (SF-UCMKF).

Keywords: Measurement conversion, Doppler, Kalman filter, estimation, tracking.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 375

Authors: Hermenegilde Nkurunziza, Albrecht Gebhardt, Juergen Pilz

Abstract:

The focus in this work is to assess which method allows a better forecasting of malaria cases in Bujumbura ( Burundi) when taking into account association between climatic factors and the disease. For the period 1996-2007, real monthly data on both malaria epidemiology and climate in Bujumbura are described and analyzed. We propose a hierarchical approach to achieve our objective. We first fit a Generalized Additive Model to malaria cases to obtain an accurate predictor, which is then used to predict future observations. Various well-known forecasting methods are compared leading to different results. Based on in-sample mean average percentage error (MAPE), the multiplicative exponential smoothing state space model with multiplicative error and seasonality performed better.

Keywords: Burundi, Forecasting, Malaria, Regressionmodel, State space model.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1983

Authors: Serkawt Khola

Abstract:

A feature weighting and selection method is proposed which uses the structure of a weightless neuron and exploits the principles that govern the operation of Genetic Algorithms and Evolution. Features are coded onto chromosomes in a novel way which allows weighting information regarding the features to be directly inferred from the gene values. The proposed method is significant in that it addresses several problems concerned with algorithms for feature selection and weighting as well as providing significant advantages such as speed, simplicity and suitability for real-time systems.

Keywords: Feature weighting, genetic algorithm, pattern recognition, weightless neuron.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1854

Authors: Ondrej Baran, Miroslav Kasal, Petr Vagner, Tomas Urbanec

Abstract:

This paper deals with the modeling and the evaluation of a multiplicative phase noise influence on the bit error ratio in a general space communication system. Our research is focused on systems with multi-state phase shift keying modulation techniques and it turns out, that the phase noise significantly affects the bit error rate, especially for higher signal to noise ratios. These results come from a system model created in Matlab environment and are shown in a form of constellation diagrams and bit error rate dependencies. The change of a user data bit rate is also considered and included into simulation results. Obtained outcomes confirm theoretical presumptions.

Keywords: Additive thermal noise, AWGN, BER, bit error rate, multiplicative phase noise, phase shift keying.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 4612

Authors: Djalal Eddine Khodja, Boukhemis Chetate

Abstract:

In this paper, an automatic system of diagnosis was developed to detect and locate in real time the defects of the wound rotor asynchronous machine associated to electronic converter. For this purpose, we have treated the signals of the measured parameters (current and speed) to use them firstly, as indicating variables of the machine defects under study and, secondly, as inputs to the Artificial Neuron Network (ANN) for their classification in order to detect the defect type in progress. Once a defect is detected, the interpretation system of information will give the type of the defect and its place of appearance.

Keywords: Artificial Neuron Networks (ANN), Effective Value (RMS), Experimental results, Failure detection Indicating values, Motor-converter unit.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1499

Authors: Faris Tarlochan, Siva Mahesh Tangutooru

Abstract:

Lateral Geniculate Nucleus (LGN) is the relay center in the visual pathway as it receives most of the input information from retinal ganglion cells (RGC) and sends to visual cortex. Low threshold calcium currents (IT) at the membrane are the unique indicator to characterize this firing functionality of the LGN neurons gained by the RGC input. According to the LGN functional requirements such as functional mapping of RGC to LGN, the morphologies of the LGN neurons were developed. During the neurological disorders like glaucoma, the mapping between RGC and LGN is disconnected and hence stimulating LGN electrically using deep brain electrodes can restore the functionalities of LGN. A computational model was developed for simulating the LGN neurons with three predominant morphologies each representing different functional mapping of RGC to LGN. The firings of action potentials at LGN neuron due to IT were characterized by varying the stimulation parameters, morphological parameters and orientation. A wide range of stimulation parameters (stimulus amplitude, duration and frequency) represents the various strengths of the electrical stimulation with different morphological parameters (soma size, dendrites size and structure). The orientation (0-1800) of LGN neuron with respect to the stimulating electrode represents the angle at which the extracellular deep brain stimulation towards LGN neuron is performed. A reduced dendrite structure was used in the model using Bush–Sejnowski algorithm to decrease the computational time while conserving its input resistance and total surface area. The major finding is that an input potential of 0.4 V is required to produce the action potential in the LGN neuron which is placed at 100 μm distance from the electrode. From this study, it can be concluded that the neuroprostheses under design would need to consider the capability of inducing at least 0.4V to produce action potentials in LGN.

Keywords: Lateral geniculate nucleus, visual cortex, finite element, glaucoma, neuroprostheses.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2024

Authors: Bertrand Fontaine, Herbert Peremans

Abstract:

Mammals are known to use Interaural Intensity Difference (IID) to determine azimuthal position of high frequency sounds. In the Lateral Superior Olive (LSO) neurons have firing behaviours which vary systematicaly with IID. Those neurons receive excitatory inputs from the ipsilateral ear and inhibitory inputs from the contralateral one. The IID sensitivity of a LSO neuron is thought to be due to delay differences between both ears, delays due to different synaptic delays and to intensity-dependent delays. In this paper we model the auditory pathway until the LSO. Inputs to LSO neurons are at first numerous and differ in their relative delays. Spike Timing-Dependent Plasticity is then used to prune those connections. We compare the pruned neuron responses with physiological data and analyse the relationship between IID-s of teacher stimuli and IID sensitivities of trained LSO neurons.

Keywords: Interaural difference, lateral superior olive, spike time-dependent plasticity.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1477

Authors: A. Mirzaaghazadeh, H. Motameni, M. Karshenas, H. Nematzadeh

Abstract:

Learning the gradient of neuron's activity function like the weight of links causes a new specification which is flexibility. In flexible neural networks because of supervising and controlling the operation of neurons, all the burden of the learning is not dedicated to the weight of links, therefore in each period of learning of each neuron, in fact the gradient of their activity function, cooperate in order to achieve the goal of learning thus the number of learning will be decreased considerably. Furthermore, learning neurons parameters immunes them against changing in their inputs and factors which cause such changing. Likewise initial selecting of weights, type of activity function, selecting the initial gradient of activity function and selecting a fixed amount which is multiplied by gradient of error to calculate the weight changes and gradient of activity function, has a direct affect in convergence of network for learning.

Keywords: Back propagation, Flexible, Gradient, Learning, Neural network, Pattern recognition.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1493

Authors: Sinarwati Mohamad Suhaili, Naomie Salim, Mohamad Nazim Jambli

Abstract:

Sequence-to-sequence (seq2seq) models augmented with attention mechanisms are increasingly important in automated customer service. These models, adept at recognizing complex relationships between input and output sequences, are essential for optimizing chatbot responses. Central to these mechanisms are neural attention weights that determine the model’s focus during sequence generation. Despite their widespread use, there remains a gap in the comparative analysis of different attention weighting functions within seq2seq models, particularly in the context of chatbots utilizing the Customer Support Twitter (CST) dataset. This study addresses this gap by evaluating four distinct attention-scoring functions—dot, multiplicative/general, additive, and an extended multiplicative function with a tanh activation parameter — in neural generative seq2seq models. Using the CST dataset, these models were trained and evaluated over 10 epochs with the AdamW optimizer. Evaluation criteria included validation loss and BLEU scores implemented under both greedy and beam search strategies with a beam size of k = 3. Results indicate that the model with the tanh-augmented multiplicative function significantly outperforms its counterparts, achieving the lowest validation loss (1.136484) and the highest BLEU scores (0.438926 under greedy search, 0.443000 under beam search, k = 3). These findings emphasize the crucial influence of selecting an appropriate attention-scoring function to enhance the performance of seq2seq models for chatbots, particularly highlighting the model integrating tanh activation as a promising approach to improving chatbot quality in customer support contexts.

Keywords: Attention weight, chatbot, encoder-decoder, neural generative attention, score function, sequence-to-sequence.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 89

Authors: Syed Muhammad Aqil Burney, Tahseen Ahmed Jilani, C. Ardil

Abstract:

Using neural network we try to model the unknown function f for given input-output data pairs. The connection strength of each neuron is updated through learning. Repeated simulations of crisp neural network produce different values of weight factors that are directly affected by the change of different parameters. We propose the idea that for each neuron in the network, we can obtain quasi-fuzzy weight sets (QFWS) using repeated simulation of the crisp neural network. Such type of fuzzy weight functions may be applied where we have multivariate crisp input that needs to be adjusted after iterative learning, like claim amount distribution analysis. As real data is subjected to noise and uncertainty, therefore, QFWS may be helpful in the simplification of such complex problems. Secondly, these QFWS provide good initial solution for training of fuzzy neural networks with reduced computational complexity.

Keywords: Crisp neural networks, fuzzy systems, extraction of logical rules, quasi-fuzzy numbers.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1739

Authors: A. Belayadi, A. Mougari, L. Ait-Gougam, F. Mekideche-Chafa

Abstract:

The artificial neural network is one of the interesting techniques that have been advantageously used to deal with modeling problems. In this study, the computing with artificial neural network (CANN) is proposed. The model is applied to modulate the information processing of one-dimensional task. We aim to integrate a new method which is based on a new coding approach of generating the input-output mapping. The latter is based on increasing the neuron unit in the last layer. Accordingly, to show the efficiency of the approach under study, a comparison is made between the proposed method of generating the input-output set and the conventional method. The results illustrated that the increasing of the neuron units, in the last layer, allows to find the optimal network’s parameters that fit with the mapping data. Moreover, it permits to decrease the training time, during the computation process, which avoids the use of computers with high memory usage.

Keywords: Neural network computing, information processing, input-output mapping, training time, computers with high memory.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1323

Authors: A.Venkadesan, S.Himavathi, A.Muthuramalingam

Abstract:

Rotor Flux based Model Reference Adaptive System (RF-MRAS) is the most popularly used conventional speed estimation scheme for sensor-less IM drives. In this scheme, the voltage model equations are used for the reference model. This encounters major drawbacks at low frequencies/speed which leads to the poor performance of RF-MRAS. Replacing the reference model using Neural Network (NN) based flux estimator provides an alternate solution and addresses such drawbacks. This paper identifies an NN based flux estimator using Single Neuron Cascaded (SNC) Architecture. The proposed SNC-NN model replaces the conventional voltage model in RF-MRAS to form a novel MRAS scheme named as SNC-NN-MRAS. Through simulation the proposed SNC-NN-MRAS is shown to be promising in terms of all major issues and robustness to parameter variation. The suitability of the proposed SNC-NN-MRAS based speed estimator and its advantages over RF-MRAS for sensor-less induction motor drives is comprehensively presented through extensive simulations.

Keywords: Sensor-less operation, vector-controlled IM drives, SNC-NN-MRAS, single neuron cascaded architecture, RF-MRAS, artificial neural network

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1874