Search results for: Deep learning network

Authors: M. Sarrab, M. Elbasir

Abstract:

The use of information technology in education have changed not only the learners learning style but also the way they taught, where nowadays learners are connected with diversity of information sources with means of knowledge available everywhere. The advantage of network wireless technologies and mobility technologies used in the education and learning processes lead to mobile learning as a new model of learning technology. Currently, most of mobile learning applications are developed for the formal education and learning environment. Despite the long history and large amount of research on mobile learning and instruction design model still there is a need of well-defined process in designing mobile learning applications. Based on this situation, this paper emphasizes on identifying instruction design phase’s considerations and influencing factors in developing mobile learning application. This set of instruction design steps includes analysis, design, development, implementation, evaluation and continuous has been built from a literature study, with focus on standards for learning, mobile application software quality and guidelines. The effort is part of an Omani-funded research project investigating the development, adoption and dissemination of mobile learning in Oman.

Keywords: Instruction design, mobile learning, mobile application.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1689

Authors: Mousavian, M. Moghimi Mofrad, M. H. Vakili, D. Ashouri, R. Alizadeh

Abstract:

The aim of this research is to use artificial neural networks computing technology for estimating the net heating value (NHV) of crude oil by its Properties. The approach is based on training the neural network simulator uses back-propagation as the learning algorithm for a predefined range of analytically generated well test response. The network with 8 neurons in one hidden layer was selected and prediction of this network has been good agreement with experimental data.

Keywords: Neural Network, Net Heating Value, Crude Oil, Experimental, Modeling.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1588

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: Rahib Hidayat Abiyev

Abstract:

This paper presents the development of recurrent neural network based fuzzy inference system for identification and control of dynamic nonlinear plant. The structure and algorithms of fuzzy system based on recurrent neural network are described. To train unknown parameters of the system the supervised learning algorithm is used. As a result of learning, the rules of neuro-fuzzy system are formed. The neuro-fuzzy system is used for the identification and control of nonlinear dynamic plant. The simulation results of identification and control systems based on recurrent neuro-fuzzy network are compared with the simulation results of other neural systems. It is found that the recurrent neuro-fuzzy based system has better performance than the others.

Keywords: Fuzzy logic, neural network, neuro-fuzzy system, control system.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2373

Authors: Shahrinaz Ismail, Zulhelmi Mohammed, Nur Waheda Md Yusof, Mohd Sharifuddin Ahmad

Abstract:

The burst of Web 2.0 technology and social networking tools manifest different styles of learning and managing knowledge among both knowledge workers and adult learners. In the Western countries, open-learning concept has been made popular due to the ease of use and the reach that the technology provides. In Malaysia, there are still some gaps between the learners- acceptance of technology and the full implementation of the technology in the education system. There is a need to understand how adult learners, who are knowledge workers, manage their personal knowledge via social networking tools, especially in their learning process. Four processes of personal knowledge management (PKM) and four cognitive enablers are proposed supported by analysed data on adult learners in a university. The model derived from these processes and enablers is tested and presented, with recommendations on features to be included in adult learners- learning environment.

Keywords: Personal knowledge management, adult learners, social network, learning environment.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1989

Authors: Wee Hock Quik, Nevan Wright

Abstract:

Collaborative networked learning (hereafter CNL) was first proposed by Charles Findley in his work “Collaborative networked learning: online facilitation and software support" as part of instructional learning for the future of the knowledge worker. His premise was that through electronic dialogue learners and experts could interactively communicate within a contextual framework to resolve problems, and/or to improve product or process knowledge. Collaborative learning has always been the forefront of educational technology and pedagogical research, but not in the mainstream of operations management. As a result, there is a large disparity in the study of CNL, and little is known about the antecedents of network collaboration and sharing of information among diverse employees in the manufacturing environment. This paper presents a model to bridge the gap between theory and practice. The objective is that manufacturing organizations will be able to accelerate organizational learning and sharing of information through various collaborative

Keywords: Collaborative networked learning, Collaborative technologies, Organizational learning, Synchronous and asynchronous networked learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1700

Authors: Wernhuar Tarng, Weichian Tsai

Abstract:

The major purpose of this study is to use network and multimedia technologies to build a game-based learning system for junior high school students to apply in learning “World Geography" through the “role-playing" game approaches. This study first investigated the motivation and habits of junior high school students to use the Internet and online games, and then designed a game-based learning system according to situated and game-based learning theories. A teaching experiment was conducted to analyze the learning effectiveness of students on the game-based learning system and the major factors affecting their learning. A questionnaire survey was used to understand the students- attitudes towards game-based learning. The results showed that the game-based learning system can enhance students- learning, but the gender of students and their habits in using the Internet have no significant impact on learning. Game experience has a significant impact on students- learning, and the higher the experience value the better the effectiveness of their learning. The results of questionnaire survey also revealed that the system can increase students- motivation and interest in learning "World Geography".

Keywords: Game-based learning, situated learning, role playing, learning effectiveness, learning motivation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2594

Authors: Kazunari Meguro, Shinichi Motomura, Takao Kawamura, Kazunori Sugahara

Abstract:

We have developed a distributed asynchronous Web based training system. In order to improve the scalability and robustness of this system, all contents and a function are realized on mobile agents. These agents are distributed to computers, and they can use a Peer to Peer network that modified Content-Addressable Network. In this system, all computers offer the function and exercise by themselves. However, the system that all computers do the same behavior is not realistic. In this paper, as a solution of this issue, we present an e-Learning system that is composed of computers of different participation types. Enabling the computer of different participation types will improve the convenience of the system.

Keywords: Distributed Multimedia Systems, e-Learning, P2P, Mobile Agen

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2338

Authors: S. Sowmyayani

Abstract:

The advancement of computer-aided design helps the medical force and security force. Some applications include biometric recognition, elderly fall detection, face recognition, cancer recognition, tumor recognition, etc. This paper deals with different machine learning algorithms that are more generically used for any health care system. The most focused problems are classification and regression. With the rise of big data, machine learning has become particularly important for solving problems. Machine learning uses two types of techniques: supervised learning and unsupervised learning. The former trains a model on known input and output data and predicts future outputs. Classification and regression are supervised learning techniques. Unsupervised learning finds hidden patterns in input data. Clustering is one such unsupervised learning technique. The above-mentioned models are discussed briefly in this paper.

Keywords: Supervised learning, unsupervised learning, regression, neural network.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 346

Authors: Z. M. Najmi

Abstract:

Over the years, the question around Artificial Intelligence has always been one with many answers. Whether by means of use in business and industry or complicated algorithmic programming, management of these technologies has always been the core focus. More recently, technologies have been questioned in industry and society alike as to whether they have improved human-centred design, assisted choices and objectives, and had a hand in systematic processes across the board. With these questions the answer may lie within AI technologies, and the steps needed in removing common human error. Elements such as Machine Learning, Deep Learning, Recommender Systems and Natural Language Processing will all be features to consider moving forward. Our previous intervention with AI applications has resulted in increased productivity, however, raised concerns for the continuation of traditional human-centred occupations. Emerging technologies such as Augmented Reality and Virtual Reality have all played a part in this during AI’s prominent rise. As mentioned, AI has been constantly under the microscope; the benefits and drawbacks may seem endless is wide, but AI is something we must take notice of and adapt into our everyday lives. The aim of this paper is to give an overview of the technologies surrounding A.I. and its’ related technologies. A comprehensive review has been written as a timeline of the developing events and key points in the history of Artificial Intelligence. This research is gathered entirely from secondary research, academic statements of knowledge and gathered to produce an understanding of the timeline of AI.

Keywords: Artificial Intelligence, Deep Learning, Augmented Reality, Reinforcement Learning, Machine Learning, Supervised Learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 576

Authors: Fazıl Gökgöz, Fahrettin Filiz

Abstract:

Load forecasting has become crucial in recent years and become popular in forecasting area. Many different power forecasting models have been tried out for this purpose. Electricity load forecasting is necessary for energy policies, healthy and reliable grid systems. Effective power forecasting of renewable energy load leads the decision makers to minimize the costs of electric utilities and power plants. Forecasting tools are required that can be used to predict how much renewable energy can be utilized. The purpose of this study is to explore the effectiveness of LSTM-based neural networks for estimating renewable energy loads. In this study, we present models for predicting renewable energy loads based on deep neural networks, especially the Long Term Memory (LSTM) algorithms. Deep learning allows multiple layers of models to learn representation of data. LSTM algorithms are able to store information for long periods of time. Deep learning models have recently been used to forecast the renewable energy sources such as predicting wind and solar energy power. Historical load and weather information represent the most important variables for the inputs within the power forecasting models. The dataset contained power consumption measurements are gathered between January 2016 and December 2017 with one-hour resolution. Models use publicly available data from the Turkish Renewable Energy Resources Support Mechanism. Forecasting studies have been carried out with these data via deep neural networks approach including LSTM technique for Turkish electricity markets. 432 different models are created by changing layers cell count and dropout. The adaptive moment estimation (ADAM) algorithm is used for training as a gradient-based optimizer instead of SGD (stochastic gradient). ADAM performed better than SGD in terms of faster convergence and lower error rates. Models performance is compared according to MAE (Mean Absolute Error) and MSE (Mean Squared Error). Best five MAE results out of 432 tested models are 0.66, 0.74, 0.85 and 1.09. The forecasting performance of the proposed LSTM models gives successful results compared to literature searches.

Keywords: Deep learning, long-short-term memory, energy, renewable energy load forecasting.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1596

Authors: Anupama Pande, Vishik Goel

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 image and vision processing. In Neural networks, radial basis functions are often used for interpolation in multidimensional space. A Radial Basis function is a function, which has built into it a distance criterion with respect to a centre. Radial basis functions have often been applied in the area of neural networks where they may be used as a replacement for the sigmoid hidden layer transfer characteristic in multi-layer perceptron. This paper aims to present exhaustive results of using RBF units 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 Radial basis function in a complex valued neural network in image recognition 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 on a neural network model with RBF units. Some inherent properties of this complex back propagation algorithm are also studied and discussed.

Keywords: Complex valued neural network, Radial BasisFunction, Image recognition.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2410

Authors: Apoorva Vinod, Archana Mathur, Snehanshu Saha

Abstract:

Though there exists a plethora of Activation Functions (AFs) used in single and multiple hidden layer Neural Networks (NN), their behavior always raised curiosity, whether used in combination or singly. The popular AFs – Sigmoid, ReLU, and Tanh – have performed prominently well for shallow and deep architectures. Most of the time, AFs are used singly in multi-layered NN, and, to the best of our knowledge, their performance is never studied and analyzed deeply when used in combination. In this manuscript, we experiment on multi-layered NN architecture (both on shallow and deep architectures; Convolutional NN and VGG16) and investigate how well the network responds to using two different AFs (Sigmoid-Tanh, Tanh-ReLU, ReLU-Sigmoid) used alternately against a traditional, single (Sigmoid-Sigmoid, Tanh-Tanh, ReLU-ReLU) combination. Our results show that on using two different AFs, the network achieves better accuracy, substantially lower loss, and faster convergence on 4 computer vision (CV) and 15 Non-CV (NCV) datasets. When using different AFs, not only was the accuracy greater by 6-7%, but we also accomplished convergence twice as fast. We present a case study to investigate the probability of networks suffering vanishing and exploding gradients when using two different AFs. Additionally, we theoretically showed that a composition of two or more AFs satisfies Universal Approximation Theorem (UAT).

Keywords: Activation Function, Universal Approximation function, Neural Networks, convergence.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 154

Authors: Tonislav Ivanov, Oleksii Nedashkivskyi, Denis Babeshko, Vadim Pinskiy, Matthew Putman

Abstract:

Training a machine learning model for object detection that generalizes well is known to benefit from a training dataset with diverse examples. However, training datasets usually contain many repeats of common examples of a class and lack rarely seen examples. This is due to the process commonly used during human annotation where a person would proceed sequentially through a list of images labeling a sufficiently high total number of examples. Instead, the method presented involves an active process where, after the initial labeling of several images is completed, the next subset of images for labeling is selected by an algorithm. This process of algorithmic image selection and manual labeling continues in an iterative fashion. The algorithm used for the image selection is a deep learning algorithm, based on the U-shaped architecture, which quantifies the presence of unseen data in each image in order to find images that contain the most novel examples. Moreover, the location of the unseen data in each image is highlighted, aiding the labeler in spotting these examples. Experiments performed using semiconductor wafer data show that labeling a subset of the data, curated by this algorithm, resulted in a model with a better performance than a model produced from sequentially labeling the same amount of data. Also, similar performance is achieved compared to a model trained on exhaustive labeling of the whole dataset. Overall, the proposed approach results in a dataset that has a diverse set of examples per class as well as more balanced classes, which proves beneficial when training a deep learning model.

Keywords: Computer vision, deep learning, object detection, semiconductor.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 825

Authors: O. Siriporn, S. Benjawan

Abstract:

This paper represents four unsupervised clustering algorithms namely sIB, RandomFlatClustering, FarthestFirst, and FilteredClusterer that previously works have not been used for network traffic classification. The methodology, the result, the products of the cluster and evaluation of these algorithms with efficiency of each algorithm from accuracy are shown. Otherwise, the efficiency of these algorithms considering form the time that it use to generate the cluster quickly and correctly. Our work study and test the best algorithm by using classify traffic anomaly in network traffic with different attribute that have not been used before. We analyses the algorithm that have the best efficiency or the best learning and compare it to the previously used (K-Means). Our research will be use to develop anomaly detection system to more efficiency and more require in the future.

Keywords: Unsupervised, clustering, anomaly, machine learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2111

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 1805

Authors: Christian Endisch, Christoph Hackl, Dierk Schröder

Abstract:

This paper presents an exact pruning algorithm with adaptive pruning interval for general dynamic neural networks (GDNN). GDNNs are artificial neural networks with internal dynamics. All layers have feedback connections with time delays to the same and to all other layers. The structure of the plant is unknown, so the identification process is started with a larger network architecture than necessary. During parameter optimization with the Levenberg- Marquardt (LM) algorithm irrelevant weights of the dynamic neural network are deleted in order to find a model for the plant as simple as possible. The weights to be pruned are found by direct evaluation of the training data within a sliding time window. The influence of pruning on the identification system depends on the network architecture at pruning time and the selected weight to be deleted. As the architecture of the model is changed drastically during the identification and pruning process, it is suggested to adapt the pruning interval online. Two system identification examples show the architecture selection ability of the proposed pruning approach.

Keywords: System identification, dynamic neural network, recurrentneural network, GDNN, optimization, Levenberg Marquardt, realtime recurrent learning, network pruning, quasi-online learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1936

Authors: Ming-Jen Huang, Chun-Fang Huang, Chiching Wei

Abstract:

With the recent advance of the deep neural network, we observe new applications of NLP (natural language processing) and CV (computer vision) powered by deep neural networks for processing business documents. However, creating a real-world document processing system needs to integrate several NLP and CV tasks, rather than treating them separately. There is a need to have a unified approach for processing documents containing textual and graphical elements with rich formats, diverse layout arrangement, and distinct semantics. In this paper, a framework that fulfills this unified approach is presented. The framework includes a representation model definition for holding the information generated by various tasks and specifications defining the coordination between these tasks. The framework is a blueprint for building a system that can process documents with rich formats, styles, and multiple types of elements. The flexible and lightweight design of the framework can help build a system for diverse business scenarios, such as contract monitoring and reviewing.

Keywords: Document processing, framework, formal definition, machine learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 637

Authors: Thinh Ngo, Paul Rad, Brian Kelley

Abstract:

Noise estimation is essential in today wireless systems for power control, adaptive modulation, interference suppression and quality of service. Deep learning (DL) has already been applied in the physical layer for modulation and signal classifications. Unacceptably low accuracy of less than 50% is found to undermine traditional application of DL classification for SNR prediction. In this paper, we use divide-and-conquer algorithm and classifier fusion method to simplify SNR classification and therefore enhances DL learning and prediction. Specifically, multiple CNNs are used for classification rather than a single CNN. Each CNN performs a binary classification of a single SNR with two labels: less than, greater than or equal. Together, multiple CNNs are combined to effectively classify over a range of SNR values from −20 ≤ SNR ≤ 32 dB.We use pre-trained CNNs to predict SNR over a wide range of joint channel parameters including multiple Doppler shifts (0, 60, 120 Hz), power-delay profiles, and signal-modulation types (QPSK,16QAM,64-QAM). The approach achieves individual SNR prediction accuracy of 92%, composite accuracy of 70% and prediction convergence one order of magnitude faster than that of traditional estimation.

Keywords: Classification, classifier fusion, CNN, Deep Learning, prediction, SNR.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 720

Authors: M. Zerikat, M. Bendjebbar, N. Benouzza

Abstract:

In this paper, a novel approach for robust trajectory tracking of induction motor drive is presented. By combining variable structure systems theory with fuzzy logic concept and neural network techniques, a new algorithm is developed. Fuzzy logic was used for the adaptation of the learning algorithm to improve the robustness of learning and operating of the neural network. The developed control algorithm is robust to parameter variations and external influences. It also assures precise trajectory tracking with the prescribed dynamics. The algorithm was verified by simulation and the results obtained demonstrate the effectiveness of the designed controller of induction motor drives which considered as highly non linear dynamic complex systems and variable characteristics over the operating conditions.

Keywords: Induction motor, fuzzy-logic control, neural network control, indirect field oriented control.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2460

Authors: Ulas Vural, M. Ergun Okay, E. Mesut Yildiz

Abstract:

Telecommunication service providers demand accurate and precise prediction of customer churn probabilities to increase the effectiveness of their customer relation services. The large amount of customer data owned by the service providers is suitable for analysis by machine learning methods. In this study, expenditure data of customers are analyzed by using an artificial neural network (ANN). The ANN model is applied to the data of customers with different billing duration. The proposed model successfully predicts the churn probabilities at 83% accuracy for only three months expenditure data and the prediction accuracy increases up to 89% when the nine month data is used. The experiments also show that the accuracy of ANN model increases on an extended feature set with information of the changes on the bill amounts.

Keywords: Customer relationship management, churn prediction, telecom industry, deep learning, Artificial Neural Networks, ANN.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 760

Authors: Suk-Hyun Yu, Heeyong Kwon

Abstract:

Recently PM-10 has become a social and global issue. It is one of major air pollutants which affect human health. Therefore, it needs to be forecasted rapidly and precisely. However, PM-10 comes from various emission sources, and its level of concentration is largely dependent on meteorological and geographical factors of local and global region, so the forecasting of PM-10 concentration is very difficult. Neural network model can be used in the case. But, there are few cases of high concentration PM-10. It makes the learning of the neural network model difficult. In this paper, we suggest a simple input balancing method when the data distribution is uneven. It is based on the probability of appearance of the data. Experimental results show that the input balancing makes the neural networks’ learning easy and improves the forecasting rates.

Keywords: AI, air quality prediction, neural networks, pattern recognition, PM-10.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 826

Authors: Yahya H. Zweiri

Abstract:

The back-propagation algorithm calculates the weight changes of an artificial neural network, and a two-term algorithm with a dynamically optimal learning rate and a momentum factor is commonly used. Recently the addition of an extra term, called a proportional factor (PF), to the two-term BP algorithm was proposed. The third term increases the speed of the BP algorithm. However, the PF term also reduces the convergence of the BP algorithm, and optimization approaches for evaluating the learning parameters are required to facilitate the application of the three terms BP algorithm. This paper considers the optimization of the new back-propagation algorithm by using derivative information. A family of approaches exploiting the derivatives with respect to the learning rate, momentum factor and proportional factor is presented. These autonomously compute the derivatives in the weight space, by using information gathered from the forward and backward procedures. The three-term BP algorithm and the optimization approaches are evaluated using the benchmark XOR problem.

Keywords: Neural Networks, Backpropagation, Optimization.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1541

Authors: Mohamed Akrout, Douglas Tweed

Abstract:

The great success of deep learning relies on efficient optimizers, which are the algorithms that decide how to adjust network weights and biases based on gradient information. One of the most effective and widely used optimizers in recent years has been the method of adaptive moments, or Adam, but the mathematical reasons behind its effectiveness are still unclear. Attempts to analyse its behaviour have remained incomplete, in part because they hinge on a conjecture which has never been proven, regarding ratios of powers of the first and second moments of the gradient. Here we show that this conjecture is in fact false, but that a modified version of it is true, and can take its place in analyses of Adam.

Keywords: Adam optimizer, Bock’s conjecture, stochastic optimization, average regret.

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

Authors: Mohammadhosein Hasanbeig, Lacra Pavel

Abstract:

In this paper, we study a distributed control algorithm for the problem of unknown area coverage by a network of robots. The coverage objective is to locate a set of targets in the area and to minimize the robots’ energy consumption. The robots have no prior knowledge about the location and also about the number of the targets in the area. One efficient approach that can be used to relax the robots’ lack of knowledge is to incorporate an auxiliary learning algorithm into the control scheme. A learning algorithm actually allows the robots to explore and study the unknown environment and to eventually overcome their lack of knowledge. The control algorithm itself is modeled based on game theory where the network of the robots use their collective information to play a non-cooperative potential game. The algorithm is tested via simulations to verify its performance and adaptability.

Keywords: Distributed control, game theory, multi-agent learning, reinforcement learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 973

Authors: Sepideh Fazeli, Fariba Bahrami

Abstract:

Investigating language acquisition is one of the most challenging problems in the area of studying language. Syllable learning as a level of language acquisition has a considerable significance since it plays an important role in language acquisition. Because of impossibility of studying language acquisition directly with children, especially in its developmental phases, computer models will be useful in examining language acquisition. In this paper a computer model of early language learning for syllable learning is proposed. It is guided by a conceptual model of syllable learning which is named Directions Into Velocities of Articulators model (DIVA). The computer model uses simple associational and reinforcement learning rules within neural network architecture which are inspired by neuroscience. Our simulation results verify the ability of the proposed computer model in producing phonemes during babbling and early speech. Also, it provides a framework for examining the neural basis of language learning and communication disorders.

Keywords: Brain modeling, computer models, language acquisition, reinforcement learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1589

Authors: Yi-Chun Chang, Jian-Wei Li

Abstract:

Web-based cooperative learning focuses on (1) the interaction and the collaboration of community members, and (2) the sharing and the distribution of knowledge and expertise by network technology to enhance learning performance. Numerous research literatures related to web-based cooperative learning have demonstrated that cooperative scripts have a positive impact to specify, sequence, and assign cooperative learning activities. Besides, literatures have indicated that role-play in web-based cooperative learning environments enhances two or more students to work together toward the completion of a common goal. Since students generally do not know each other and they lack the face-to-face contact that is necessary for the negotiation of assigning group roles in web-based cooperative learning environments, this paper intends to further extend the application of genetic algorithm (GA) and propose a GA-based algorithm to tackle the problem of role assignment in web-based cooperative learning environments, which not only saves communication costs but also reduces conflict between group members in negotiating role assignments.

Keywords: genetic algorithm (GA), role assignment, role-play; web-based cooperative learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1459

Authors: R. N. Begum, Ambalika Sharma, G. K. Singh

Abstract:

Identity theft has serious ramifications beyond data and personal information loss. This necessitates the implementation of robust and efficient user identification systems. Therefore, automatic biometric recognition systems are the need of the hour, and electrocardiogram (ECG)-based systems are unquestionably the best choice due to their appealing inherent characteristics. The Convolutional Neural Networks (CNNs) are the recent state-of-the-art techniques for ECG-based user identification systems. However, the results obtained are significantly below standards, and the situation worsens as the number of users and types of heartbeats in the dataset grows. As a result, this study proposes a highly accurate and resilient ECG-based person identification system using CNN's dense learning framework. The proposed research explores explicitly the caliber of dense CNNs in the field of ECG-based human recognition. The study tests four different configurations of dense CNN which are trained on a dataset of recordings collected from eight popular ECG databases. With the highest False Acceptance Rate (FAR)  of 0.04% and the highest False Rejection Rate (FRR)  of 5%, the best performing network achieved an identification accuracy of 99.94%. The best network is also tested with various train/test split ratios. The findings show that DenseNets are not only extremely reliable, but also highly efficient. Thus, they might also be implemented in real-time ECG-based human recognition systems.

Keywords: Biometrics, dense networks, identification rate, train/test split ratio.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 541

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: Nuntaporn Aukkanit

Abstract:

The aim of this study was to determine the effect of oils on chemical, physical, and sensory properties of deep-fried dough stick. Five kinds of vegetable oil which were used for addition and frying consist of: palm oil, soybean oil, sunflower oil, rice bran oil, and canola oil. The results of this study showed that using different kinds of oil made significant difference in the quality of deep-fried dough stick. Deep-fried dough stick fried with the rice bran oil had the lowest moisture loss and oil absorption (p≤0.05), but it had some unsatisfactory physical properties (color, specific volume, density, and texture) and sensory characteristics. Nonetheless, deep-fried dough stick fried with the sunflower oil had moisture loss and oil absorption slightly more than the rice bran oil, but it had almost higher physical and sensory properties. Deep-fried dough sticks together with the sunflower oil did not have different sensory score from the palm oil, commonly used for production of deep-fried dough stick. These results indicated that addition and frying with the sunflower oil are appropriate for the production of deep-fried dough stick.

Keywords: Deep-fried dough stick, palm oil, sunflower oil, rice bran oil.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1851