Search results for: probabilistic neural network(PNN)

Authors: Zongyan Li, Matt Best

Abstract:

This paper presents an optimization method for reducing the number of input channels and the complexity of the feed-forward NARX neural network (NN) without compromising the accuracy of the NN model. By utilizing the correlation analysis method, the most significant regressors are selected to form the input layer of the NN structure. An application of vehicle dynamic model identification is also presented in this paper to demonstrate the optimization technique and the optimal input layer structure and the optimal number of neurons for the neural network is investigated.

Keywords: Correlation analysis, F-ratio, Levenberg-Marquardt, MSE, NARX, neural network, optimisation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2188

Authors: Hadi Firouzi, Majid Nili Ahmadabadi, Babak N. Araabi

Abstract:

Conceptualization strengthens intelligent systems in generalization skill, effective knowledge representation, real-time inference, and managing uncertain and indefinite situations in addition to facilitating knowledge communication for learning agents situated in real world. Concept learning introduces a way of abstraction by which the continuous state is formed as entities called concepts which are connected to the action space and thus, they illustrate somehow the complex action space. Of computational concept learning approaches, action-based conceptualization is favored because of its simplicity and mirror neuron foundations in neuroscience. In this paper, a new biologically inspired concept learning approach based on the probabilistic framework is proposed. This approach exploits and extends the mirror neuron-s role in conceptualization for a reinforcement learning agent in nondeterministic environments. In the proposed method, instead of building a huge numerical knowledge, the concepts are learnt gradually from rewards through interaction with the environment. Moreover the probabilistic formation of the concepts is employed to deal with uncertain and dynamic nature of real problems in addition to the ability of generalization. These characteristics as a whole distinguish the proposed learning algorithm from both a pure classification algorithm and typical reinforcement learning. Simulation results show advantages of the proposed framework in terms of convergence speed as well as generalization and asymptotic behavior because of utilizing both success and failures attempts through received rewards. Experimental results, on the other hand, show the applicability and effectiveness of the proposed method in continuous and noisy environments for a real robotic task such as maze as well as the benefits of implementing an incremental learning scenario in artificial agents.

Keywords: Concept learning, probabilistic decision making, reinforcement learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1527

Authors: Motonobu Hattori

Abstract:

In neural networks, when new patterns are learned by a network, the new information radically interferes with previously stored patterns. This drawback is called catastrophic forgetting or catastrophic interference. In this paper, we propose a biologically inspired neural network model which overcomes this problem. The proposed model consists of two distinct networks: one is a Hopfield type of chaotic associative memory and the other is a multilayer neural network. We consider that these networks correspond to the hippocampus and the neocortex of the brain, respectively. Information given is firstly stored in the hippocampal network with fast learning algorithm. Then the stored information is recalled by chaotic behavior of each neuron in the hippocampal network. Finally, it is consolidated in the neocortical network by using pseudopatterns. Computer simulation results show that the proposed model has much better ability to avoid catastrophic forgetting in comparison with conventional models.

Keywords: catastrophic forgetting, chaotic neural network, complementary learning systems, dual-network

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2102

Authors: Miaomiao Yang, Shouming Zhong

Abstract:

This paper studies the problem of asymptotically stability for neural networks with time-varying delays.By establishing a suitable Lyapunov-Krasovskii function and several novel sufficient conditions are obtained to guarantee the asymptotically stability of the considered system. Finally,two numerical examples are given to illustrate the effectiveness of the proposed main results.

Keywords: Neural networks, Lyapunov-Krasovskii, Time-varying delays, Linear matrix inequality.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1719

Authors: K. Sreelakshmi, P. Ramakanthkumar

Abstract:

Predicting short term wind speed is essential in order to prevent systems in-action from the effects of strong winds. It also helps in using wind energy as an alternative source of energy, mainly for Electrical power generation. Wind speed prediction has applications in Military and civilian fields for air traffic control, rocket launch, ship navigation etc. The wind speed in near future depends on the values of other meteorological variables, such as atmospheric pressure, moisture content, humidity, rainfall etc. The values of these parameters are obtained from a nearest weather station and are used to train various forms of neural networks. The trained model of neural networks is validated using a similar set of data. The model is then used to predict the wind speed, using the same meteorological information. This paper reports an Artificial Neural Network model for short term wind speed prediction, which uses back propagation algorithm.

Keywords: Short term wind speed prediction, Neural networks, Back propagation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3065

Authors: Peng Li, Jun Zhou, Xin Liu, Chee Keong Ho, Xiaodan Zou, Minkyu Je

Abstract:

A digital system is proposed for low power 100- channel neural recording system in this paper, which consists of 100 amplifiers, 100 analog-to-digital converters (ADC), digital controller and baseband, transceiver for data link and RF command link. The proposed system is designed in a 0.18 μm CMOS process and 65 nm CMOS process.

Keywords: multiplex, neural recording, synchronization, transceiver

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1652

Authors: Amir Abolfazl Suratgar, Mohammad Bagher Tavakoli, Abbas Hoseinabadi

Abstract:

In this paper a modification on Levenberg-Marquardt algorithm for MLP neural network learning is proposed. The proposed algorithm has good convergence. This method reduces the amount of oscillation in learning procedure. An example is given to show usefulness of this method. Finally a simulation verifies the results of proposed method.

Keywords: Levenberg-Marquardt, modification, neural network, variable learning rate.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 5046

Authors: Sajjad Farashi, Mohammadjavad Abolhassani, Mostafa Taghavi Kani

Abstract:

Information in the nervous system is coded as firing patterns of electrical signals called action potential or spike so an essential step in analysis of neural mechanism is detection of action potentials embedded in the neural data. There are several methods proposed in the literature for such a purpose. In this paper a novel method based on empirical mode decomposition (EMD) has been developed. EMD is a decomposition method that extracts oscillations with different frequency range in a waveform. The method is adaptive and no a-priori knowledge about data or parameter adjusting is needed in it. The results for simulated data indicate that proposed method is comparable with wavelet based methods for spike detection. For neural signals with signal-to-noise ratio near 3 proposed methods is capable to detect more than 95% of action potentials accurately.

Keywords: EMD, neural data processing, spike detection, wavelet decomposition.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2374

Authors: A. Johannet, B. Vayssade, D. Bertin

Abstract:

Neural networks are well known for their ability to model non linear functions, but as statistical methods usually does, they use a no parametric approach thus, a priori knowledge is not obvious to be taken into account no more than the a posteriori knowledge. In order to deal with these problematics, an original way to encode the knowledge inside the architecture is proposed. This method is applied to the problem of the evapotranspiration inside karstic aquifer which is a problem of huge utility in order to deal with water resource.

Keywords: Neural-Networks, Hydrology, Evapotranpiration, Hidden Function Modeling.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1807

Authors: Han Bing, Yin Zhenjie

Abstract:

In order to analyze the status of a diesel engine, as well as conduct fault prediction, a new prediction model based on a gray system is proposed in this paper, which takes advantage of the neural network and the genetic algorithm. The proposed GBPGA prediction model builds on the GM (1.5) model and uses a neural network, which is optimized by a genetic algorithm to construct the error compensator. We verify our proposed model on the diesel faulty simulation data and the experimental results show that GBPGA has the potential to employ fault prediction on diesel.

Keywords: Fault prediction, Neural network, GM (1.5), Genetic algorithm, GBPGA.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1302

Authors: Ozlem Faydasicok, Sabri Arik

Abstract:

This paper derives some new sufficient conditions for the stability of a class of neutral-type neural networks with discrete time delays by employing a suitable Lyapunov functional. The obtained conditions can be easily verified as they can be expressed in terms of the network parameters only. It is shown that the results presented in this paper for neutral-type delayed neural networks establish a new set of stability criteria, and therefore can be considered as the alternative results to the previously published literature results. A numerical example is also given to demonstrate the applicability of our proposed stability criterion.

Keywords: Stability Analysis, Neutral-Type Neural Networks, Time Delay Systems, Lyapunov Functionals.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1638

Authors: A. Schuster

Abstract:

Many artificial intelligence (AI) techniques are inspired by problem-solving strategies found in nature. Robustness is a key feature in many natural systems. This paper studies robustness in artificial neural networks (ANNs) and proposes several novel, nature inspired ANN architectures. The paper includes encouraging results from experimental studies on these networks showing increased robustness.

Keywords: robustness, robust artificial neural networks architectures.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1407

Authors: K.Sedhuraman, S.Himavathi, A.Muthuramalingam

Abstract:

The performance of sensor-less controlled induction motor drive depends on the accuracy of the estimated speed. Conventional estimation techniques being mathematically complex require more execution time resulting in poor dynamic response. The nonlinear mapping capability and powerful learning algorithms of neural network provides a promising alternative for on-line speed estimation. The on-line speed estimator requires the NN model to be accurate, simpler in design, structurally compact and computationally less complex to ensure faster execution and effective control in real time implementation. This in turn to a large extent depends on the type of Neural Architecture. This paper investigates three types of neural architectures for on-line speed estimation and their performance is compared in terms of accuracy, structural compactness, computational complexity and execution time. The suitable neural architecture for on-line speed estimation is identified and the promising results obtained are presented.

Keywords: Sensorless IM drives, rotor speed estimators, artificial neural network, feed- forward architecture, single neuron cascaded architecture.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1458

Authors: Nerijus Remeikis, Ignas Skucas, Vida Melninkaite

Abstract:

Text categorization - the assignment of natural language documents to one or more predefined categories based on their semantic content - is an important component in many information organization and management tasks. Performance of neural networks learning is known to be sensitive to the initial weights and architecture. This paper discusses the use multilayer neural network initialization with decision tree classifier for improving text categorization accuracy. An adaptation of the algorithm is proposed in which a decision tree from root node until a final leave is used for initialization of multilayer neural network. The experimental evaluation demonstrates this approach provides better classification accuracy with Reuters-21578 corpus, one of the standard benchmarks for text categorization tasks. We present results comparing the accuracy of this approach with multilayer neural network initialized with traditional random method and decision tree classifiers.

Keywords: Text categorization, decision trees, neural networks, machine learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1806

Authors: H.Mohammadi Majd, M.Jalali Azizpour , Foad Saadi

Abstract:

In this paper back-propagation artificial neural network (BPANN) is employed to predict the deformation of the upsetting process. To prepare a training set for BPANN, some finite element simulations were carried out. The input data for the artificial neural network are a set of parameters generated randomly (aspect ratio d/h, material properties, temperature and coefficient of friction). The output data are the coefficient of polynomial that fitted on barreling curves. Neural network was trained using barreling curves generated by finite element simulations of the upsetting and the corresponding material parameters. This technique was tested for three different specimens and can be successfully employed to predict the deformation of the upsetting process

Keywords: Back-propagation artificial neural network(BPANN), prediction, upsetting

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1552

Authors: Travis Wiens, Greg Schoenau, Rich Burton

Abstract:

It is well known that a linear dynamic system including a delay will exhibit limit cycle oscillations when a bang-bang sensor is used in the feedback loop of a PID controller. A similar behaviour occurs when a delayed feedback signal is used to train a neural network. This paper develops a method of predicting this behaviour by linearizing the system, which can be shown to behave in a manner similar to an integral controller. Using this procedure, it is possible to predict the characteristics of the neural network driven limit cycle to varying degrees of accuracy, depending on the information known about the system. An application is also presented: the intelligent control of a spark ignition engine.

Keywords: Control and automation, artificial neural networks, limit cycle

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1278

Authors: Wael M. El-Mamlouk, Metwally A. El-Sharkawy, Hossam. E. Mostafa

Abstract:

In this paper, we analyze and test a scheme for the estimation of electrical fundamental frequency signals from the harmonic load current and voltage signals. The scheme was based on using two different Multi Layer Artificial Neural Networks (ML-ANN) one for the current and the other for the voltage. This study also analyzes and tests the effect of choosing the optimum artificial neural networks- sizes which determine the quality and accuracy of the estimation of electrical fundamental frequency signals. The simulink tool box of the Matlab program for the simulation of the test system and the test of the neural networks has been used.

Keywords: Harmonics, Neural Networks, Modeling, Simulation, Active filters, electric Networks.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1594

Authors: Hossein Esbati, Jalil Shirazi

Abstract:

In this paper, in order to categorize ORL database face pictures, principle Component Analysis (PCA) and Kernel Principal Component Analysis (KPCA) methods by using Elman neural network and Support Vector Machine (SVM) categorization methods are used. Elman network as a recurrent neural network is proposed for modeling storage systems and also it is used for reviewing the effect of using PCA numbers on system categorization precision rate and database pictures categorization time. Categorization stages are conducted with various components numbers and the obtained results of both Elman neural network categorization and support vector machine are compared. In optimum manner 97.41% recognition accuracy is obtained.

Keywords: Face recognition, Principal Component Analysis, Kernel Principal Component Analysis, Neural network, Support Vector Machine.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1930

Authors: M. Govindarajan, R. M. Chandrasekaran

Abstract:

Text Mining is around applying knowledge discovery techniques to unstructured text is termed knowledge discovery in text (KDT), or Text data mining or Text Mining. In Neural Network that address classification problems, training set, testing set, learning rate are considered as key tasks. That is collection of input/output patterns that are used to train the network and used to assess the network performance, set the rate of adjustments. This paper describes a proposed back propagation neural net classifier that performs cross validation for original Neural Network. In order to reduce the optimization of classification accuracy, training time. The feasibility the benefits of the proposed approach are demonstrated by means of five data sets like contact-lenses, cpu, weather symbolic, Weather, labor-nega-data. It is shown that , compared to exiting neural network, the training time is reduced by more than 10 times faster when the dataset is larger than CPU or the network has many hidden units while accuracy ('percent correct') was the same for all datasets but contact-lences, which is the only one with missing attributes. For contact-lences the accuracy with Proposed Neural Network was in average around 0.3 % less than with the original Neural Network. This algorithm is independent of specify data sets so that many ideas and solutions can be transferred to other classifier paradigms.

Keywords: Back propagation, classification accuracy, textmining, time complexity.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 4218

Authors: M. Mohagheghian, A. M. Ghaedi, A. Vafaei

Abstract:

An artificial neural network (ANN) model is presented for the prediction of kinematic viscosity of binary mixtures of poly (ethylene glycol) (PEG) in water as a function of temperature, number-average molecular weight and mass fraction. Kinematic viscosities data of aqueous solutions for PEG (0.55419×10-6 – 9.875×10-6 m2/s) were obtained from the literature for a wide range of temperatures (277.15 - 338.15 K), number-average molecular weight (200 -10000), and mass fraction (0.0 – 1.0). A three layer feed-forward artificial neural network was employed. This model predicts the kinematic viscosity with a mean square error (MSE) of 0.281 and the coefficient of determination (R2) of 0.983. The results show that the kinematic viscosity of binary mixture of PEG in water could be successfully predicted using an artificial neural network model.

Keywords: Artificial neural network, kinematic viscosity, poly ethylene glycol (PEG)

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2530

Authors: Akram M. Othman, May H. Riadh

Abstract:

This research work is aimed at speech recognition using scaly neural networks. A small vocabulary of 11 words were established first, these words are “word, file, open, print, exit, edit, cut, copy, paste, doc1, doc2". These chosen words involved with executing some computer functions such as opening a file, print certain text document, cutting, copying, pasting, editing and exit. It introduced to the computer then subjected to feature extraction process using LPC (linear prediction coefficients). These features are used as input to an artificial neural network in speaker dependent mode. Half of the words are used for training the artificial neural network and the other half are used for testing the system; those are used for information retrieval. The system components are consist of three parts, speech processing and feature extraction, training and testing by using neural networks and information retrieval. The retrieve process proved to be 79.5-88% successful, which is quite acceptable, considering the variation to surrounding, state of the person, and the microphone type.

Keywords: Feature extraction, Liner prediction coefficients, neural network, Speech Recognition, Scaly ANN.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1737

Authors: Farouk Cherif

Abstract:

This paper is concerned with the existence and unique¬ness of pseudo-almost periodic solutions to the chaotic delayed neural networks (t)= —Dx(t) ± A f (x (t)) B f (x (t — r)) C f (x(p))dp J (t) . t-o Under some suitable assumptions on A, B, C, D, J and f, the existence and uniqueness of a pseudo-almost periodic solution to equation above is obtained. The results of this paper are new and they complement previously known results.

Keywords: Chaotic neural network, Hamiltonian systems, Pseudo almost periodic.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1310

Authors: Fengxia Zheng, Shouming Zhong

Abstract:

ANNARIMA that combines both autoregressive integrated moving average (ARIMA) model and artificial neural network (ANN) model is a valuable tool for modeling and forecasting nonlinear time series, yet the over-fitting problem is more likely to occur in neural network models. This paper provides a hybrid methodology that combines both radial basis function (RBF) neural network and auto regression (AR) model based on binomial smoothing (BS) technique which is efficient in data processing, which is called BSRBFAR. This method is examined by using the data of Canadian Lynx data. Empirical results indicate that the over-fitting problem can be eased using RBF neural network based on binomial smoothing which is called BS-RBF, and the hybrid model–BS-RBFAR can be an effective way to improve forecasting accuracy achieved by BSRBF used separately.

Keywords: Binomial smoothing (BS), hybrid, Canadian Lynx data, forecasting accuracy.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3686

Authors: H.Mohammadi Majd, M.Jalali Azizpour

Abstract:

In this paper back-propagation artificial neural network (BPANN )with Levenberg–Marquardt algorithm is employed to predict the deformation of the upsetting process. To prepare a training set for BPANN, some finite element simulations were carried out. The input data for the artificial neural network are a set of parameters generated randomly (aspect ratio d/h, material properties, temperature and coefficient of friction). The output data are the coefficient of polynomial that fitted on barreling curves. Neural network was trained using barreling curves generated by finite element simulations of the upsetting and the corresponding material parameters. This technique was tested for three different specimens and can be successfully employed to predict the deformation of the upsetting process

Keywords: Back-propagation artificial neural network(BPANN), prediction, upsetting

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1789

Authors: Qingqing Wang, Baocheng Chen, Shouming Zhong

Abstract:

In this paper,the exponential passivity criteria for BAM neural networks with time-varying delays is studied.By constructing new Lyapunov-Krasovskii functional and dividing the delay interval into multiple segments,a novel sufficient condition is established to guarantee the exponential stability of the considered system.Finally,a numerical example is provided to illustrate the usefulness of the proposed main results

Keywords: BAM neural networks, Exponential passivity, LMI approach, Time-varying delays.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1908

Authors: J. Fernandez de Canete, S. Gonzalez-Perez, P. del Saz-Orozco, I. Garcia-Moral

Abstract:

Robust stability and performance are the two most basic features of feedback control systems. The harmonic balance analysis technique enables to analyze the stability of limit cycles arising from a neural network control based system operating over nonlinear plants. In this work a robust stability analysis based on the harmonic balance is presented and applied to a neural based control of a non-linear binary distillation column with unstructured uncertainty. We develop ways to describe uncertainty in the form of neglected nonlinear dynamics and high harmonics for the plant and controller respectively. Finally, conclusions about the performance of the neural control system are discussed using the Nyquist stability margin together with the structured singular values of the uncertainty as a robustness measure.

Keywords: Robust stability, neural network control, unstructured uncertainty, singular values, distillation column.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1628

Authors: M. Sinecen, M. Makinacı

Abstract:

The purpose of this paper is to assess the value of neural networks for classification of cancer and noncancer prostate cells. Gauss Markov Random Fields, Fourier entropy and wavelet average deviation features are calculated from 80 noncancer and 80 cancer prostate cell nuclei. For classification, artificial neural network techniques which are multilayer perceptron, radial basis function and learning vector quantization are used. Two methods are utilized for multilayer perceptron. First method has single hidden layer and between 3-15 nodes, second method has two hidden layer and each layer has between 3-15 nodes. Overall classification rate of 86.88% is achieved.

Keywords: Artificial neural networks, texture classification, cancer diagnosis.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1591

Authors: Farhad Asadi, S. Hossein Sadati

Abstract:

This paper presents a prediction performance of feedforward Multilayer Perceptron (MLP) and Echo State Networks (ESN) trained with extended Kalman filter. Feedforward neural networks and ESN are powerful neural networks which can track and predict nonlinear signals. However, their tracking performance depends on the specific signals or data sets, having the risk of instability accompanied by large error. In this study we explore this process by applying different network size and leaking rate for prediction of nonlinear or chaotic signals in MLP neural networks. Major problems of ESN training such as the problem of initialization of the network and improvement in the prediction performance are tackled. The influence of coefficient of activation function in the hidden layer and other key parameters are investigated by simulation results. Extended Kalman filter is employed in order to improve the sequential and regulation learning rate of the feedforward neural networks. This training approach has vital features in the training of the network when signals have chaotic or non-stationary sequential pattern. Minimization of the variance in each step of the computation and hence smoothing of tracking were obtained by examining the results, indicating satisfactory tracking characteristics for certain conditions. In addition, simulation results confirmed satisfactory performance of both of the two neural networks with modified parameterization in tracking of the nonlinear signals.

Keywords: Feedforward neural networks, nonlinear signal prediction, echo state neural networks approach, leaking rates, capacity of neural networks.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 758

Authors: A. Denker, U. Akıncıoğlu

Abstract:

In this paper a neural adaptive control method has been developed and applied to robot control. Simulation results are presented to verify the effectiveness of the controller. These results show that the performance by using this controller is better than those which just use either direct inverse control or predictive control. In addition, they show that the resulting is a useful method which combines the advantages of both direct inverse control and predictive control.

Keywords: Neural networks, robotics, direct inverse control, predictive control.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2184

Authors: Jie Zhao, Meng Su

Abstract:

Image recognition enables machine-like robotics to understand a scene and plays an important role in computer vision applications. Computer vision platforms as physical infrastructure, supporting Neural Networks for image recognition, are deterministic to leverage the performance of different Neural Networks. In this paper, three different computer vision platforms – edge AI (Jetson Nano, with 4GB), a standalone laptop (with RTX 3000s, using CUDA), and a web-based device (Google Colab, using GPU) are investigated. In the case study, four prominent neural network architectures (including AlexNet, VGG16, GoogleNet, and ResNet (34/50)), are deployed. By using public ImageNets (Cifar-10), our findings provide a nuanced perspective on optimizing image recognition tasks across Edge-AI platforms, offering guidance on selecting appropriate neural network structures to maximize performance under hardware constraints.

Keywords: AlexNet, VGG, GoogleNet, ResNet, ImageNet, Cifar-10, Edge AI, Jetson Nano, CUDA, GPU.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 220