الصفحة 1
الصفحة 1
New insights in machine learning and deep neural networks
Gatheres ten exemplary papers, each delineating advancements within the spheres of machine learning and deep neural networks. Commencing with a thorough exploration by Figueira and Vaz, readers are introduced to the nuances of synthetic data generation and evaluation, followed closely by Silva and Pedroso's systematic approach to leveraging deep reinforcement learning within the intricate realm of delivery logistics. Kamran et al. contribute an astute methodology for camouflage object segmentation, whereas Pinheiro and collaborators offer a crafted semi-supervised strategy for predicting EGFR mutations via CT images. Subsequent contributions, such as Lee and Yoo's framework for portrait emotion recognition and Balakrishnan et al.'s analytical exploration of transformer models for Twitter disaster detection, further exemplify the depth of research contained herein.
Neural networks and deep learning
Covers both classical and modern models in deep learning. The primary focus is on the theory and algorithms of deep learning. The theory and algorithms of neural networks are particularly important for understanding important concepts, so that one can understand the important design concepts of neural architectures in different applications. Why do neural networks work? When do they work better than off-the-shelf machine-learning models? When is depth useful? Why is training neural networks so hard? What are the pitfalls? The book is also rich in discussing different applications in order to give the practitioner a flavor of how neural architectures are designed for different types of problems.
Neural Information Processing ; 14th International Conference, ICONIP 2007, Kitakyushu, Japan, November 13-16, 2007, Revised Selected Papers, Part II
The 228 revised full papers presented were carefully reviewed and selected from numerous ordinary paper submissions and 15 special organized sessions. The 116 papers of the first volume are organized in topical sections on computational neuroscience, learning and memory, neural network models ,supervised /unsupervised/reinforcement learning, statistical learning algorithms, optimization algorithms, novel algorithms, as well as motor control and vision. The second volume contains 112 contributions related to statistical and pattern recognition algorithms, neuromorphic hardware and implementations, robotics, data mining and knowledge discovery, real world applications, cognitive and hybrid intelligent systems, bioinformatics, neuroinformatics, brain-conputer interfaces, and novel approaches.
Neural Information Processing ; 14th International Conference, ICONIP 2007, Kitakyushu, Japan, November 13-16, 2007, Revised Selected Papers, Part I
The 228 revised full papers presented were carefully reviewed and selected from numerous ordinary paper submissions and 15 special organized sessions. The 116 papers of the first volume are organized in topical sections on computational neuroscience, learning and memory, neural network models, supervised/unsupervised/reinforcement learning, statistical learning algorithms, optimization algorithms, novel algorithms, as well as motor control and vision. The second volume contains 112 contributions related to statistical and pattern recognition algorithms, neuromorphic hardware and implementations, robotics, data mining and knowledge discovery, real world applications, cognitive and hybrid intelligent systems, bioinformatics, neuroinformatics, brain-conputer interfaces, and novel approaches.
Mobile Robots : The Evolutionary Approach
The design and control of autonomous intelligent mobile robotic systems operating in unstructured changing environments includes many objective difficulties. There are several studies about the ways in which, robots exhibiting some degree of autonomy, adapt themselves to fit in their environments. The application and use of bio-inspired and intelligent techniques such as reinforcement learning, artificial neural networks, evolutionary computation and so forth in the design and improvement of robot designs is an emergent research topic. Researchers have obtained robots that display an amazing slew of behaviours and perform a multitude of tasks. These include perception of environment, planning and navigation in rough terrain, pushing boxes, negotiating an obstacle course, etc.
Intelligent cryptocurrency trading assistant
With blockchain being invented in 2008, cryptocurrencies have grown steadily through the years. Cryptocurrencies continue today to be an extremely interesting phenomenon. Having quickly achieved popularity and becoming very popular, cryptocurrencies continue to be a profitable investment tool, capable of generating huge profits on exchanges and transactions. Being a professional trader is not an easy task to achieve, a professional trader needs to observe and process multiple factors and events that affect the cryptocurrency market to make the right decision. What makes this process challenging is that some of the factors cannot be predicted or calculated but rather, their changes should be observed and comprehended, and an action should be taken in response quickly in order to maximize the profit or minimize the loss.
Intelligent Computing Theories and Application ; 16th International Conference, ICIC 2020, Bari, Italy, October 2–5, 2020, Proceedings, Part I
This two-volume set of LNCS 12463 and LNCS 12464 constitutes - in conjunction with the volume LNAI 12465 - the refereed proceedings of the 16th International Conference on Intelligent Computing, ICIC 2020, held in Bari, Italy, in October 2020. The 162 full papers of the three proceedings volumes were carefully reviewed and selected from 457 submissions The ICIC theme unifies the picture of contemporary intelligent computing techniques as an integral concept that highlights the trends in advanced computational intelligence and bridges theoretical research with applications. The theme for this conference is “Advanced Intelligent Computing Methodologies and Applications.” Papers related to this theme are especially solicited, addressing theories, methodologies, and applications in science and technology.
Intelligent Algorithms for Packing and Cutting Problem
Introduces intelligent solving algorithms for classical packing and cutting problem and their variants / Investigates novel methods, e.g. reinforcement learning algorithms, for rectangular and irregular packing problems / Presents practical engineering application cases in combination of theory and practice / investigates in detail the two-dimensional packing and cutting problems in the field of operations research and management science. It introduces the mathematical models and intelligent solving algorithms for these problems, as well as their engineering applications. Most intelligent methods reported in this book have already been applied in reality, which can provide reference for the engineers. The presented novel methods for the two-dimensional packing problem provide a new way to solve the problem for researchers interested in operations research or computer science. This book also introduces three new variants of packing problems and their solving methods, which offer a different research direction.
Inductive logic programming ; 17th International Conference, ILP 2007, Corvallis, OR, USA, June 19-21, 2007, Revised Selected Papers
The 18th International Conference on Inductive Logic Programming was held in Prague, September 10–12, 2008. ILP returned to Prague after 11 years, and it is tempting to look at how the topics of interest have evolved during that time. The ILP community clearly continues to cherish its beloved ?rst-order logic representation framework. This is legitimate, as the work presented at ILP 2008 demonstrated that there is still room for both extending established ILP approaches (such as inverse entailment) and exploring novel logic induction frameworks (such as brave induction). Besides the topics lending ILP research its unique focus.
Image and video processing and recognition based on artificial intelligence (Vol. II)
Focuses on challenging issues in the field of AI-based image and video processing and recognition, including the topics of AI-based image processing, understanding, recognition, compression, and reconstruction; AI-based video processing, understanding, recognition, compression, and reconstruction; computer vision based on AI; AI-based biometrics; AI-based object detection and tracking; approaches that combine AI techniques and conventional methods for image and video processing and recognition; explainable AI (XAI) for image and video processing and recognition; generative adversarial network (GAN)-based image and video processing and recognition; and approaches that combine AI techniques and blockchain methods for image and video processing and recognition.
Hyperparameter tuning for machine and deep learning with R : A practical guide
Equips readers with the ability to achieve better results with significantly less time, costs, effort and resources using the methods described here. The case studies presented in this book can be run on a regular desktop or notebook computer. The content focuses on the hyperparameter tuning of ML and DL algorithms, and is divided into two main parts: theory (Part I) and application (Part II). Essential topics covered include: a survey of important model parameters; four parameter tuning studies and one extensive global parameter tuning study; statistical analysis of the performance of ML and DL methods based on severity; and a new, consensus-ranking-based way to aggregate and analyze results from multiple algorithms.
High accuracy detection of mobile malware using machine learning
As increasingly sophisticated and evasive malware attacks continue to emerge, more effective detection solutions to tackle the problem are being sought through the application of advanced machine learning techniques. This reprint presents several advances in the field including: a new method of generating adversarial samples through byte sequence feature extraction using deep learning; a state-of-the-art comparative evaluation of deep learning approaches for mobile botnet detection; a novel visualization-based approach that utilizes images for Android botnet detection; a study on the detection of drive-by exploits in images using deep learning; etc. Furthermore, this reprint presents state-of-the-art reviews about machine learning-based detection techniques that will increase researchers' knowledge in the field and enable them to identify future research and development directions.
Green, pervasive, and cloud computing ; 15th International conference, GPC 2020, Xi'an, China, November 13–15, 2020, Proceedings
This book constitutes the refereed proceedings of the 15th International Conference on Green, Pervasive, and Cloud Computing, GPC 2020, held in Xi'an, China, in November 2020. The 30 full papers presented in this book together with 8 short papers were carefully reviewed and selected from 96 submissions. They cover the following topics: Device-free Sensing; Machine Learning; Recommendation Systems; Urban Computing; Human Computer Interaction; Internet of Things and Edge Computing; Positioning; Applications of Computer Vision; CrowdSensing; and Cloud and Related Technologies.
Foundations of learning classifier systems
This volume brings together recent theoretical work in Learning Classifier Systems (LCS), which is a Machine Learning technique combining Genetic Algorithms and Reinforcement Learning. It includes self-contained background chapters on related fields (reinforcement learning and evolutionary computation) tailored for a classifier systems audience and written by acknowledged authorities in their area - as well as a relevant historical original work by John Holland.
Dynamic pricing and automated resource allocation for complex information services : Reinforcement learning and combinatorial auctions
This book develops allocation mechanisms that aim to ensure an efficient resource allocation in modern IT-services. The author presents two methods, both of which using the users’ willingness-to-pay to control the allocation process. The author generates a method to calculate dynamic resource prices.
Distributed artificial intelligence ; 2nd International conference, DAI 2020, Nanjing, China, October 24–27, 2020, Proceedings
This book constitutes the refereed proceedings of the Second International Conference on Distributed Artificial Intelligence, DAI 2020, held in Nanjing, China, in October 2020. The 9 full papers presented in this book were carefully reviewed and selected from 22 submissions. DAI aims at bringing together international researchers and practitioners in related areas including general AI, multiagent systems, distributed learning, computational game theory, etc., to provide a single, high-profile, internationally renowned forum for research in the theory and practice of distributed AI.
Digital twin : Architectures, networks, and applications
Offers comprehensive, self-contained knowledge on digital twin (DT), which is a very promising technology for achieving digital intelligence in the next-generation wireless communications and computing networks. DT is a key technology to connect physical systems and digital spaces in Metaverse. The objectives of this book are to provide the basic concepts of DT, to explore the promising applications of DT integrated with emerging technologies, and to give insights into the possible future directions of DT. For easy understanding, this book also presents several use cases for DT models and applications in different scenarios. The book starts with the basic concepts, models, and network architectures of DT. Then, we present the new opportunities when DT meets edge computing, Blockchain and Artificial Intelligence, and distributed machine learning (e.g., federated learning, multi-agent deep reinforcement learning).
Design and Analysis of Learning Classifier Systems : A Probabilistic Approach
This book provides a comprehensive introduction to the design and analysis of Learning Classifier Systems (LCS) from the perspective of machine learning. LCS are a family of methods for handling unsupervised learning, supervised learning and sequential decision tasks by decomposing larger problem spaces into easy-to-handle subproblems.
Deep learning architecture and application
As one of the fastest-growing topics in machine learning, deep learning algorithms have achieved unprecedented success in recent years. Novel paradigms (such as contrastive learning and few-shot learning) in deep learning and rising neural network architectures (e.g., transformer and masked autoencoder) are dramatically changing the field of data-driven algorithms. More importantly, deep learning models are redefining the next generation of industrial applications spanning image recognition, speech processing, language translation, healthcare, and other sciences. For example, recent advances in deep representation learning are allowing us to learn about protein 3D structures, which sheds new light on fundamental medicine and biology along with potentially bringing in billions of dollars (e.g., in the pharmaceutical market).
Data mining : Concepts, models, methods, and algorithms ; 3rd ed.
Presents the latest techniques for analyzing and extracting information from large amounts of data in high-dimensional data spaces. Explores big data and cloud computing Examines deep learning Includes information on convolutional neural networks (CNN) Offers reinforcement learning Contains semi-supervised learning and S3VM Reviews model evaluation for unbalanced data
