{"title":"Deep Reinforcement Learning for Optimization","authors":"M. Hasan, Md Shahinur Rahman, A. Bell","doi":"10.4018/978-1-5225-7862-8.CH011","DOIUrl":"https://doi.org/10.4018/978-1-5225-7862-8.CH011","url":null,"abstract":"Deep reinforcement learning (DRL) has transformed the field of artificial intelligence (AI) especially after the success of Google DeepMind. This branch of machine learning epitomizes a step toward building autonomous systems by understanding of the visual world. Deep reinforcement learning (RL) is currently applied to different sorts of problems that were previously obstinate. In this chapter, at first, the authors started with an introduction of the general field of RL and Markov decision process (MDP). Then, they clarified the common DRL framework and the necessary components RL settings. Moreover, they analyzed the stochastic gradient descent (SGD)-based optimizers such as ADAM and a non-specific multi-policy selection mechanism in a multi-objective Markov decision process. In this chapter, the authors also included the comparison for different Deep Q networks. In conclusion, they describe several challenges and trends in research within the deep reinforcement learning field.","PeriodicalId":104292,"journal":{"name":"Handbook of Research on Deep Learning Innovations and Trends","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116327469","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Malware Classification and Analysis Using Convolutional and Recurrent Neural Network","authors":"Yassine Maleh","doi":"10.4018/978-1-5225-7862-8.CH014","DOIUrl":"https://doi.org/10.4018/978-1-5225-7862-8.CH014","url":null,"abstract":"Over the past decade, malware has grown exponentially. Traditional signature-based approaches to detecting malware have proven their limitations against new malware, and categorizing malware samples has become essential to understanding the basics of malware behavior. Recently, antivirus solutions have increasingly started to adopt machine learning approaches. Unfortunately, there are few open source data sets available for the academic community. One of the largest data sets available was published last year in a competition on Kaggle with data provided by Microsoft for the big data innovators gathering. This chapter explores the problem of malware classification. In particular, this chapter proposes an innovative and scalable approach using convolutional neural networks (CNN) and long short-term memory (LSTM) to assign malware to the corresponding family. The proposed method achieved a classification accuracy of 98.73% and an average log loss of 0.0698 on the validation data.","PeriodicalId":104292,"journal":{"name":"Handbook of Research on Deep Learning Innovations and Trends","volume":"106 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128098469","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Deep Clustering","authors":"M. P. Boobalan","doi":"10.4018/978-1-5225-7862-8.ch010","DOIUrl":"https://doi.org/10.4018/978-1-5225-7862-8.ch010","url":null,"abstract":"Clustering is an unsupervised technique used in various application, namely machine learning, image segmentation, social network analysis, health analytics, and financial analysis. It is a task of grouping similar objects together and dissimilar objects in different group. The quality of the cluster relies on two factors: distance metrics and data representation. Deep learning is a new field of machine learning research that has been introduced to move machine learning closer to artificial intelligence. Learning using deep network provides multiple layers of representation that helps to understand images, sound, and text. In this chapter, the need for deep network in clustering, various architecture, and algorithms for unsupervised learning is discussed.","PeriodicalId":104292,"journal":{"name":"Handbook of Research on Deep Learning Innovations and Trends","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129319509","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A Survey on Deep Learning Techniques Used for Quality Process","authors":"Vanyashree Mardi, E. Naresh, B. P. V. Kumar","doi":"10.4018/978-1-5225-7862-8.CH008","DOIUrl":"https://doi.org/10.4018/978-1-5225-7862-8.CH008","url":null,"abstract":"In the current era, software development and software quality has become extensively important for implementing the real-world software application, and it will enhance the software functionality. Moreover, early prediction of expected error and fault level in the quality process is critical to the software development process. Deep learning techniques are the most appropriate methods for this problem, and this chapter carries out an extensive systematic survey on a variety of deep learning. These techniques are used in the software quality process along with a hypothesis justification for each of the proposed solutions. The deep learning and machine learning techniques are considered to be the most suitable systems for software quality prediction. Deep learning is a computational model made up of various hidden layers of investigation used to portray of information with the goal that researchers can better understand complex information issues.","PeriodicalId":104292,"journal":{"name":"Handbook of Research on Deep Learning Innovations and Trends","volume":"114 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132539233","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Enhanced Footsteps Generation Method for Walking Robots Based on Convolutional Neural Networks","authors":"S. Savin, Aleksei Ivakhnenko","doi":"10.4018/978-1-5225-7862-8.CH002","DOIUrl":"https://doi.org/10.4018/978-1-5225-7862-8.CH002","url":null,"abstract":"In this chapter, the problem of finding a suitable foothold for a bipedal walking robot is studied. There are a number of gait generation algorithms that rely on having a set of obstacle-free regions where the robot can step to and there are a number of algorithms for generating these regions. This study breaches the gap between these algorithms, providing a way to quickly check if a given obstacle free region is accessible for foot placement. The proposed approach is based on the use of a classifier, constructed as a convolutional neural network. The study discusses the training dataset generation, including datasets with uncertainty related to the shapes of the obstacle-free regions. Training results for a number of different datasets and different hyperparameter choices are presented and showed robustness of the proposed network design both to different hyperparameter choices as well as to the changes in the training dataset.","PeriodicalId":104292,"journal":{"name":"Handbook of Research on Deep Learning Innovations and Trends","volume":"211 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132873819","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
R. Janghel, S. Sahu, Y. Rathore, Shraddha Singh, Urja Pawar
{"title":"Application of Deep Learning in Speech Recognition","authors":"R. Janghel, S. Sahu, Y. Rathore, Shraddha Singh, Urja Pawar","doi":"10.4018/978-1-5225-7862-8.CH004","DOIUrl":"https://doi.org/10.4018/978-1-5225-7862-8.CH004","url":null,"abstract":"Speech is the vocalized form of communication used by humans and some animals. It is based upon the syntactic combination of items drawn from the lexicon. Each spoken word is created out of the phonetic combination of a limited set of vowel and consonant speech sound units (phonemes). Here, the authors propose a deep learning model used on tensor flow speech recognition dataset, which consist of 30 words. Here, 2D convolutional neural network (CNN) model is used for understanding simple spoken commands using the speech commands dataset by tensor flow. Dataset is divided into 70% training and 30% testing data. While running the algorithm for three epochs average accuracy of 92.7% is achieved.","PeriodicalId":104292,"journal":{"name":"Handbook of Research on Deep Learning Innovations and Trends","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130583966","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Transfer Learning in 2.5D Face Image for Occlusion Presence and Gender Classification","authors":"Sahil Sharma, Vijay Kumar","doi":"10.4018/978-1-5225-7862-8.CH006","DOIUrl":"https://doi.org/10.4018/978-1-5225-7862-8.CH006","url":null,"abstract":"Face depth image has been used for occlusion presence and gender prediction by transfer learning. This chapter discusses about the overfitting problem and how augmentation helps overcoming it. Pre-processing of the dataset includes converting a 3D object image into depth image for further processing. Five state-of-the-art 2D deep learning models (e.g., AlexNet, VGG16, DenseNet121, ResNet18, and SqueezeNet) have been discussed along with their architecture. The effect of increasing the number of epochs on the top-1 error rate has been presented in the experimental section. The result section consists of error rates in comparison of with and without augmentation on the datasets.","PeriodicalId":104292,"journal":{"name":"Handbook of Research on Deep Learning Innovations and Trends","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124642710","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Deep Learning","authors":"Kamaljit I. Lakhtaria, Darshankumar Modi","doi":"10.4018/978-1-5225-7862-8.CH007","DOIUrl":"https://doi.org/10.4018/978-1-5225-7862-8.CH007","url":null,"abstract":"Deep learning is a subset of machine learning. As the name suggests, deep learning means more and more layers. Deep leaning basically works on the principle of neurons. With the increase in big data or large quantities of data, deep learning methods and techniques have been widely used to extract the useful information. Deep learning can be applied to computer vision, bioinformatics, and speech recognition or on natural language processing. This chapter covers the basics of deep learning, different architectures of deep learning like artificial neural network, feed forward neural network, CNN, recurrent neural network, deep Boltzmann machine, and their comparison. This chapter also summarizes the applications of deep learning in different areas.","PeriodicalId":104292,"journal":{"name":"Handbook of Research on Deep Learning Innovations and Trends","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114568880","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"CNN Customizations With Transfer Learning for Face Recognition Task","authors":"C. Chantrapornchai, Samrid Duangkaew","doi":"10.4018/978-1-5225-7862-8.CH003","DOIUrl":"https://doi.org/10.4018/978-1-5225-7862-8.CH003","url":null,"abstract":"Several kinds of pretrained convolutional neural networks (CNN) exist nowadays. Utilizing these networks with the new classification task requires the retraining with new data sets. With the small embedded device, large network cannot be implemented. The authors study the use of pretrained models and customizing them towards accuracy and size against face recognition tasks. The results show 1) the performance of existing pretrained networks (e.g., AlexNet, GoogLeNet, CaffeNet, SqueezeNet), as well as size, and 2) demonstrate the layers customization towards the model size and accuracy. The studied results show that among the various networks with different data sets, SqueezeNet can achieve the same accuracy (0.99) as others with small size (up to 25 times smaller). Secondly, the two customizations with layer skipping are presented. The experiments show the example of SqueezeNet layer customizing, reducing the network size while keeping the accuracy (i.e., reducing the size by 7% with the slower convergence time). The experiments are measured based on Caffe 0.15.14.","PeriodicalId":104292,"journal":{"name":"Handbook of Research on Deep Learning Innovations and Trends","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133279023","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}