scholarly journals Using a Reinforcement Q-Learning-Based Deep Neural Network for Playing Video Games

Electronics ◽  
2019 ◽  
Vol 8 (10) ◽  
pp. 1128 ◽  
Author(s):  
Lin ◽  
Jhang ◽  
Lee ◽  
Lin ◽  
Young
Keyword(s):  
Neural Network ◽  
Video Games ◽  
Video Game ◽  
Deep Neural Network ◽  
Principal Component ◽  
Image Features ◽  
Convolution Kernel ◽  
Training Time ◽  
Q Learning ◽  
Better Than

This study proposed a reinforcement Q-learning-based deep neural network (RQDNN) that combined a deep principal component analysis network (DPCANet) and Q-learning to determine a playing strategy for video games. Video game images were used as the inputs. The proposed DPCANet was used to initialize the parameters of the convolution kernel and capture the image features automatically. It performs as a deep neural network and requires less computational complexity than traditional convolution neural networks. A reinforcement Q-learning method was used to implement a strategy for playing the video game. Both Flappy Bird and Atari Breakout games were implemented to verify the proposed method in this study. Experimental results showed that the scores of our proposed RQDNN were better than those of human players and other methods. In addition, the training time of the proposed RQDNN was also far less than other methods.

scholarly journals SMO-DNN: Spider Monkey Optimization and Deep Neural Network Hybrid Classifier Model for Intrusion Detection

Electronics ◽  
2020 ◽  
Vol 9 (4) ◽  
pp. 692 ◽  
Author(s):  
Neelu Khare ◽  
Preethi Devan ◽  
Chiranji Chowdhary ◽  
Sweta Bhattacharya ◽  
Geeta Singh ◽  
...  
Keyword(s):  
Neural Network ◽  
Intrusion Detection ◽  
Deep Neural Network ◽  
Principal Component ◽  
Spider Monkey ◽  
Intrusion Detection Systems ◽  
Quality Of Data ◽  
Training Time ◽  
Detection Systems ◽  
Spider Monkey Optimization

The enormous growth in internet usage has led to the development of different malicious software posing serious threats to computer security. The various computational activities carried out over the network have huge chances to be tampered and manipulated and this necessitates the emergence of efficient intrusion detection systems. The network attacks are also dynamic in nature, something which increases the importance of developing appropriate models for classification and predictions. Machine learning (ML) and deep learning algorithms have been prevalent choices in the analysis of intrusion detection systems (IDS) datasets. The issues pertaining to quality and quality of data and the handling of high dimensional data is managed by the use of nature inspired algorithms. The present study uses a NSL-KDD and KDD Cup 99 dataset collected from the Kaggle repository. The dataset was cleansed using the min-max normalization technique and passed through the 1-N encoding method for achieving homogeneity. A spider monkey optimization (SMO) algorithm was used for dimensionality reduction and the reduced dataset was fed into a deep neural network (DNN). The SMO based DNN model generated classification results with 99.4% and 92% accuracy, 99.5%and 92.7% of precision, 99.5% and 92.8% of recall and 99.6%and 92.7% of F1-score, utilizing minimal training time. The model was further compared with principal component analysis (PCA)-based DNN and the classical DNN models, wherein the results justified the advantage of implementing the proposed model over other approaches.

scholarly journals A Novel Approach for Efficient Training of Deep Neural Networks

2018 ◽  
Vol 11 (3) ◽  
pp. 954
Author(s):  
D.T.V. Dharmajee Rao ◽  
K.V. Ramana
Keyword(s):  
Neural Network ◽  
Deep Neural Network ◽  
Programming Model ◽  
Optimization Technique ◽  
Matrix Multiplication ◽  
Training Algorithms ◽  
Training Time ◽  
Large Matrix ◽  
Novel Approach ◽  
Parallel Programming Model

<p style="text-indent: 1.27cm; margin-bottom: 0.35cm; line-height: 115%;" align="justify"><span style="font-family: Arial,serif;"><span style="font-size: small;"><em>Deep Neural Network training algorithms consumes long training time, especially when the number of hidden layers and nodes is large. Matrix multiplication is the key operation carried out at every node of each layer for several hundreds of thousands of times during the training of Deep Neural Network. Blocking is a well-proven optimization technique to improve the performance of matrix multiplication. Blocked Matrix multiplication algorithms can easily be parallelized to accelerate the performance further. This paper proposes a novel approach of implementing Parallel Blocked Matrix multiplication algorithms to reduce the long training time. The proposed approach was implemented using a parallel programming model OpenMP with collapse() clause for the multiplication of input and weight matrices of Backpropagation and Boltzmann Machine Algorithms for training Deep Neural Network and tested on multi-core processor system. Experimental results showed that the proposed approach achieved approximately two times speedup than classic algorithms.</em></span></span></p>

scholarly journals Research on Quality Anomaly Recognition Method Based on Optimized Probabilistic Neural Network

2020 ◽  
Vol 2020 ◽  
pp. 1-11 ◽  
Author(s):  
Li-li Li ◽  
Kun Chen ◽  
Jian-min Gao ◽  
Hui Li
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Control Chart ◽  
Control Charts ◽  
Probabilistic Neural Network ◽  
Principal Component ◽  
Original Data ◽  
Improved Genetic Algorithm ◽  
Training Time ◽  
Mixed Pattern

Aiming at the problems of the lack of abnormal instances and the lag of quality anomaly discovery in quality database, this paper proposed the method of recognizing quality anomaly from the quality control chart data by probabilistic neural network (PNN) optimized by improved genetic algorithm, which made up deficiencies of SPC control charts in practical application. Principal component analysis (PCA) reduced the dimension and extracted the feature of the original data of a control chart, which reduced the training time of PNN. PNN recognized successfully both single pattern and mixed pattern of control charts because of its simple network structure and excellent recognition effect. In order to eliminate the defect of experience value, the key parameter of PNN was optimized by the improved (SGA) single-target optimization genetic algorithm, which made PNN achieve a higher rate of recognition accuracy than PNN optimized by standard genetic algorithm. Finally, the above method was validated by a simulation experiment and proved to be the most effective method compared with traditional BP neural network, single PNN, PCA-PNN without parameters optimized, and SVM optimized by particle swarm optimization algorithm.

scholarly journals A parametric texture model based on deep convolutional features closely matches texture appearance for humans

2017 ◽  
Author(s):  
Thomas S. A. Wallis ◽  
Christina M. Funke ◽  
Alexander S. Ecker ◽  
Leon A. Gatys ◽  
Felix A. Wichmann ◽  
...  
Keyword(s):  
Neural Network ◽  
Power Spectrum ◽  
Material Properties ◽  
Image Features ◽  
Visual Environment ◽  
Texture Model ◽  
Appearance Matching ◽  
Deep Cnn ◽  
Inspection Condition ◽  
Better Than

Our visual environment is full of texture—“stuff” like cloth, bark or gravel as distinct from “things” like dresses, trees or paths—and humans are adept at perceiving subtle variations in material properties. To investigate image features important for texture perception, we psychophysically compare a recent parameteric model of texture appearance (CNN model) that uses the features encoded by a deep convolutional neural network (VGG-19) with two other models: the venerable Portilla and Simoncelli model (PS) and an extension of the CNN model in which the power spectrum is additionally matched. Observers discriminated model-generated textures from original natural textures in a spatial three-alternative oddity paradigm under two viewing conditions: when test patches were briefly presented to the near-periphery (“parafoveal”) and when observers were able to make eye movements to all three patches (“inspection”). Under parafoveal viewing, observers were unable to discriminate 10 of 12 original images from CNN model images, and remarkably, the simpler PS model performed slightly better than the CNN model (11 textures). Under foveal inspection, matching CNN features captured appearance substantially better than the PS model (9 compared to 4 textures), and including the power spectrum improved appearance matching for two of the three remaining textures. None of the models we test here could produce indiscriminable images for one of the 12 textures under the inspection condition. While deep CNN (VGG-19) features can often be used to synthesise textures that humans cannot discriminate from natural textures, there is currently no uniformly best model for all textures and viewing conditions.

scholarly journals TRIGONOMETRIC SERIES IN ORTHOGONAL EXPANSIONS FOR DENSITY ESTIMATES OF DEEP IMAGE FEATURES

2018 ◽  
Vol 42 (1) ◽  
pp. 149-158 ◽  
Author(s):  
A. V. Savchenko
Keyword(s):  
Neural Network ◽  
Trigonometric Series ◽  
Probabilistic Neural Network ◽  
Principal Component ◽  
Image Features ◽  
Small Samples ◽  
Deep Convolutional Neural Networks ◽  
Orthogonal Expansions ◽  
Computational Speed ◽  
Reference Images

In this paper we study image recognition tasks in which the images are described by high dimensional feature vectors extracted with deep convolutional neural networks and principal component analysis. In particular, we focus on the problem of high computational complexity of a statistical approach with non-parametric estimates of probability density implemented by the probabilistic neural network. We propose a novel statistical classification method based on the density estimators with orthogonal expansions using trigonometric series. It is shown that this approach makes it possible to overcome the drawbacks of the probabilistic neural network caused by the memory-based approach of instance-based learning. Our experimental study with Caltech-101 and CASIA WebFace datasets demonstrates that the proposed approach reduces the error rate by 1–5 % and increases the computational speed by 1.5 – 6 times when compared to the original probabilistic neural network for small samples of reference images.

scholarly journals Tensorflow vs R: A Comparative Study of Usability

2017 ◽  
Author(s):  
Luís Dias ◽  
Rosalvo Neto
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Comparative Study ◽  
Scientific Community ◽  
Deep Neural Network ◽  
Network Algorithms ◽  
Learning Framework ◽  
Usability Tests ◽  
Usability Analysis ◽  
Better Than

Google released on November of 2015 Tensorflow, an open source machine learning framework that can be used to implement Deep Neural Network algorithms, a class of algorithms that shows great potential in solving complex problems. Considering the importance of usability in software success, this research aims to perform a usability analysis on Tensorflow and to compare it with another widely used framework, R. The evaluation was performed through usability tests with university students. The study led do indications that Tensorflow usability is equal or better than the usability of traditional frameworks used by the scientific community.

scholarly journals Predictive Model for Brain Stroke in CT using Deep Neural Network

2020 ◽  
Vol 9 (1) ◽  
pp. 2011-2017
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Deep Neural Network ◽  
Principal Component ◽  
World Population ◽  
Neural Network Learning ◽  
Machine Learning Classification ◽  
Network Learning ◽  
Brain Stroke ◽  
Aging World

The increasing in the incidence of stroke with aging world population would quickly place an economic burden on society. In proposed method we use different machine learning classification algorithms like Decision Tree, Deep Neural Network Learning, Maximum Expectization , Random Forest and Gaussian Naïve Bayesian Classifier is used with associated number of attributes to estimate the occurrence of stroke disease. The present research, mainly PCA (Principal Component Analysis) algorithm is used to limit the performance and scaling used to be adopted to extract splendid context statistics from medical records. We used those reduced features to determine whether or not the patient has a stroke disorder. We compared proposed method Deep neural network learning classifier with other machine-learning methods with respect to accuracy, sensitivity and specificity that yields 86.42%, 74.89 and 88.49% respectively. Hence it can be with the aid of both patients and medical doctors to treat viable stroke.

scholarly journals BLNN: Multiscale Feature Fusion-Based Bilinear Fine-Grained Convolutional Neural Network for Image Classification of Wood Knot Defects

2021 ◽  
Vol 2021 ◽  
pp. 1-18
Author(s):  
Mingyu Gao ◽  
Fei Wang ◽  
Peng Song ◽  
Junyan Liu ◽  
DaWei Qi
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Defect Detection ◽  
Feature Fusion ◽  
Image Features ◽  
Optical Image ◽  
Training Time ◽  
Fine Grained ◽  
Detection Model ◽  
Defect Recognition

Wood defects are quickly identified from an optical image based on deep learning methodology, which effectively improves the wood utilization. The traditional neural network technique is unemployed for the wood defect detection of optical image used, which results from a long training time, low recognition accuracy, and nonautomatic extraction of defect image features. In this paper, a wood knot defect detection model (so-called BLNN) combined deep learning is reported. Two subnetworks composed of convolutional neural networks are trained by Pytorch. By using the feature extraction capabilities of the two subnetworks and combining the bilinear join operation, the fine-grained features of the image are obtained. The experimental results show that the accuracy has reached up 99.20%, and the training time is obviously reduced with the speed of defect detection about 0.0795 s/image. It indicates that BLNN has the ability to improve the accuracy of defect recognition and has a potential application in the detection of wood knot defects.

CARDIAC ADVANCED ARRYTHMIA PREDICTION SYSTEMS- CAAPS

2021 ◽  
pp. 54-55
Author(s):  
Pradeep Kumar Radhakrishnan ◽  
Gayathri Ananyajyothi Ambat ◽  
Saihrudya Samhita ◽  
Murugan U S ◽  
Tarig Ali ◽  
...  
Keyword(s):  
Neural Network ◽  
Principal Component Analysis ◽  
Support Vector Machine ◽  
Ventricular Arrhythmias ◽  
Deep Neural Network ◽  
Principal Component ◽  
Support Vector ◽  
Discrete Wavelet ◽  
Term Memory

There is a constant search for novel methods of classication and predicting cardiac rhythm disorders or arrhythmias. We prefer to classify them as wide complex tachyarrhythmia's or ventricular arrhythmias inclusive of malignant ventricular arrhythmias which with hemodynamic compromise is usually life threatening. Long term and fatality predictions warranting AICD implantation are already available. We have a novel method and robust algorithm with preprocessing and optimal feature selection from ECG signal analysis for such rhythm disorders. Variability of ECG recording makes predictability analysis challenging especially when execution time is of prime importance in tackling resuscitative attempts for MVA. Noisy data needs ltering and preprocessing for effective analysis. Portable devices need more of this ltering prior to data input. Deterministic probabilistic nite state automata (DPFA) which generates a probability strings from the broad morphologic patterns of an ECG can generate a classier data for the algorithm without preprocessing for atrial high rate episodes (AHRE). DPFA can be effectively used for atrial tachyarrhythmias for predictive analysis. The method we suggest is use of optimal classier set for prediction of malignant ventricular arrhythmias and use of DFPA for atrial arrhythmias. Here traditional practices of heart rate variability based support vector machine (SVM), discrete wavelet transform (DWT), principal component analysis (PCA), deep neural network (DNN), convoutional neural network (CNN) or CNN with long term memory (LSTM) can be outperformed. AICD - automatic implantable cardiac debrillator, MVA - Malignant Ventricular Arrhythmias, VT - ventricular tachycardia, VF - ventricular brillation,DFPA deterministic probabilistic nite state automata, SVM -Support Vector Machine, DWT discrete wavelet transform, PCA principal component analysis, DNN deep neural network, CNN convoutional neural network, Convoutional LSTM Long short term memory,RNN recurrent neural network

Sign in / Sign up

Export Citation Format

Share Document