Page 3
Page 3
Intelligent Computing in Engineering and Architecture ; 13th EG-ICE Workshop 2006, Ascona, Switzerland, June 25-30, 2006, Revised Selected Papers
Providing computer support for tasks in civil engineering and architecture is hard. Projects can be complex, long and costly. Firms that contribute to design, construction and maintenance are often worth less than the value of their projects. Everyone in the field is justifiably risk adverse. Contextual variables have a strong influence making generalization difficult. The product life cycle may exceed one hundred years and functional requirements may evolve during the service life. It is therefore no wonder that practitioners in this area have been so reluctant to adopt advanced computing systems. After decades of research and industrial pilot projects, advanced computing s- tems are now being recognized by many leading practitioners to be strategically - portant for the future profitability of firms involved in engineering and architecture. Engineers and architects with advanced computing knowledge are hired quickly in the market place. Closer collaboration between research and practice is leading to more comprehensive validation processes for new research ideas. This is feeding devel- ment of more useful systems, thus accelerating progress. These are exciting times. th This volume contains papers that were presented at the 13 Workshop of the Eu- pean Group for Intelligent Computing in Engineering. Over five days, 70 participants from around the world listened to 59 paper presentations in a single session format.
Intelligent Computing Everywhere
Intelligent Computing Everywhere investigates the relevance and relationship artificial intelligence maintains with "modern strands of computing" i.e. pervasive computing and ambient intelligence, bioinformatics, neuroinformatics, computing and the mind, non-classical computing and novel computing models, as well as DNA computing and quantum computing.
Intelligent Computing ; International Conference on Intelligent Computing, ICIC 2006, Kunming, China, August 16-19, 2006, Proceedings, Part I
The International Conference on Intelligent Computing (ICIC) was formed to provide an annual forum with dedication to the emerging and challenging topics in artificial intelligence, machine learning, bioinformatics, and computational biology, etc. It aims to bring together researchers and practitioners from both the academia and industry to share ideas, problems and solutions related to the multifaceted aspects of intelligent computing. The ICIC 2006 to be held in Kunming, Yunnan, China, 16-19 August 2006 is the second International Conference on Intelligent Computing, which is built upon the success of ICIC 2005 held in Hefei, China, 2005. This year, the conference mainly concentrates on the theories & methodologies as well as the emerging applications of intelligent computing. It intends to unify the contemporary intelligent computing techniques within an integral framework that highlights the trends in advanced computational intelligence and bridges the theoretical research with the applications. In particular, the bio-inspired computing emerges as a key role in pursuing for novel technology in recently years. The resulting techniques vitalize the life science engineering and daily life applications. In light of this trend, the theme for this conference is the Emerging Intelligent Computing Technology and Applications. Papers related to this theme were especially solicited, including theories, methodologies, and applications in science and technology.
Instrumaster
Experiments with different neural network structures and algorithms in order to achieve musical note recognition as well as musical instrument recognition, all bundled in a mobile application. It also aims to create the most effective music-learning application that works completely offline, which is hard to find in modern music applications. The paper also explores why the instrument identifying AI is solely based on Multi-Layer Perceptron (MLP) and why the note-identifying AI system was chosen to be a ML system over CNN or other deep-learning trained AI. The paper presents feature extraction methods for audio signals and files and dives deep into the process, such as FFT, MFCCs, Wavelengths, sampling rates, etc. It also touches on Logistic Regression Algorithms, their limitations, and their performance with the different use cases in the application. All these techniques are then compared side by side for maximally added value, making this research paper a good reference for any future developers looking to find optimal neural networks techniques when it comes to audio processing and analysis.
Inside deep learning : Math, algorithms, models
Journey through the theory and practice of modern deep learning, and apply innovative techniques to solve everyday data problems. In Inside Deep Learning, you will learn how to: Implement deep learning with PyTorch Select the right deep learning components Train and evaluate a deep learning model Fine tune deep learning models to maximize performance Understand deep learning terminology Adapt existing PyTorch code to solve new problems Inside Deep Learning is an accessible guide to implementing deep learning with the PyTorch framework. It demystifies complex deep learning concepts and teaches you to understand the vocabulary of deep learning so you can keep pace in a rapidly evolving field. No detail is skipped--you'll dive into math, theory, and practical applications. Everything is clearly explained in plain English.
Information theory and machine learning
The recent successes of machine learning, especially regarding systems based on deep neural networks, have encouraged further research activities and raised a new set of challenges in understanding and designing complex machine learning algorithms. New applications require learning algorithms to be distributed, have transferable learning results, use computation resources efficiently, convergence quickly on online settings, have performance guarantees, satisfy fairness or privacy constraints, incorporate domain knowledge on model structures, etc. A new wave of developments in statistical learning theory and information theory has set out to address these challenges.
Information Retrieval Technology ; 4th Asia Infomation Retrieval Symposium, AIRS 2008, Harbin, China, January 15-18, 2008 Revised Selected Papers
This book constitutes the thoroughly refereed post-conference proceedings of the 4th Asia Information Retrieval Symposium, AIRS 2008, held in Harbin, China, in May 2008.The 39 revised full papers and 43 revised poster papers presented were carefully reviewed and selected from 144 submissions. All current issues in information retrieval are addressed: applications, systems, technologies and theoretical aspects of information retrieval in text, audio, image, video and multi-media data. The papers are organized in topical sections on IR models image retrieval.
Information Processing with Evolutionary Algorithms : From Industrial Applications to Academic Speculations
The last decade of the 20th century has witnessed a surge of interest in num- ical, computation-intensive approaches to information processing. The lines that draw the boundaries among statistics, optimization, arti cial intelligence and information processing are disappearing, and it is not uncommon to nd well-founded and sophisticated mathematical approaches in application - mains traditionally associated with ad-hoc programming. Heuristics has - come a branch of optimization and statistics. Clustering is applied to analyze soft data and to provide fast indexing in the World Wide Web. Non-trivial matrix algebra is at the heart of the last advances in computer vision. The breakthrough impulse was, apparently, due to the rise of the interest in arti cial neural networks, after its rediscovery in the late 1980s. Disguised as ANN, numerical and statistical methods made an appearance in the - formation processing scene, and others followed. A key component in many intelligent computational processing is the search for an optimal value of some function. Sometimes, this function is not evident and it must be made explicit in order to formulate the problem as an optimization problem. The search - ten takes place in high-dimensional spaces that can be either discrete, or c- tinuous or mixed. The shape of the high-dimensional surface that corresponds to the optimized function is usually very complex. Evolutionary algorithms are increasingly being applied to information processing applications that require any kind of optimization.
Image Processing Using Pulse-Coupled Neural Networks
This is the first book to explain and demonstrate the tremendous ability of Pulse-Coupled Neural Networks (PCNNs) when applied to the field of image processing. PCNNs and their derivatives are biologically inspired models that are powerful tools for extracting texture, segments, and edges from images.
Image Analysis and Recognition ; 17th International Conference, ICIAR 2020, Póvoa de Varzim, Portugal, June 24–26, 2020, Proceedings, Part II
This two-volume set LNCS 12131 and LNCS 12132 constitutes the refereed proceedings of the 17th International Conference on Image Analysis and Recognition, ICIAR 2020, held in Póvoa de Varzim, Portugal, in June 2020. The 54 full papers presented together with 15 short papers were carefully reviewed and selected from 123 submissions. The papers are organized in the following topical sections: image processing and analysis; video analysis; computer vision; 3D computer vision; machine learning; medical image and analysis; analysis of histopathology images; diagnosis and screening of ophthalmic diseases; and grand challenge on automatic lung cancer patient management.
Image Analysis and Recognition ; 17th International Conference, ICIAR 2020, Póvoa de Varzim, Portugal, June 24–26, 2020, Proceedings, Part I
This two-volume set LNCS 12131 and LNCS 12132 constitutes the refereed proceedings of the 17th International Conference on Image Analysis and Recognition, ICIAR 2020, held in Póvoa de Varzim, Portugal, in June 2020. The 54 full papers presented together with 15 short papers were carefully reviewed and selected from 123 submissions. The papers are organized in the following topical sections: image processing and analysis; video analysis; computer vision; 3D computer vision; machine learning; medical image and analysis; analysis of histopathology images; diagnosis and screening of ophthalmic diseases; and grand challenge on automatic lung cancer patient management.
Identification of nonlinear systems using neural networks and polynomial models : A block-oriented approach
The book gives a comparative study of their gradient approximation accuracy, computational complexity, and convergence rates and furthermore presents some new and original methods concerning the model parameter adjusting with gradient-based techniques. "Identification of Nonlinear Systems Using Neural Networks and Polynomal Models".
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.
Hybrid Intelligent Systems for Pattern Recognition Using Soft Computing : An Evolutionary Approach for Neural Networks and Fuzzy Systems
This monograph describes new methods for intelligent pattern recognition using soft computing techniques including neural networks, fuzzy logic, and genetic algorithms. Hybrid intelligent systems that combine several soft computing techniques are needed due to the complexity of pattern recognition problems.
Hybrid Artificial Intelligent Systems ; 15th International Conference, HAIS 2020, Gijón, Spain, November 11-13, 2020, Proceedings
This book constitutes the refereed proceedings of the 15th International Conference on Hybrid Artificial Intelligent Systems, HAIS 2020, held in Gijón, Spain, in November 2020. The 65 regular papers presented in this book were carefully reviewed and selected from 106 submissions. The papers are grouped into these topics: advanced data processing and visualization techniques; bio-inspired models and optimization; learning algorithms; data mining, knowledge discovery and big data; and hybrid artificial intelligence applications.
High performance computational science and engineering : IFIP TC5 Workshop on High Performance Computational Science and Engineering (HPCSE), World Computer Congress, August 22-27, 2004, Toulouse, France
The IFIP series publishes state-of-the-art results in the sciences and technologies of information and communication. The scope of the series includes: foundations of computer science; software theory and practice; education; computer applications in technology; communication systems; systems modeling and optimization; information systems; computers and society; computer systems technology; security and protection in information processing systems; artificial intelligence; and human-computer interaction. Proceedings and post-proceedings of referred international conferences in computer science and interdisciplinary fields are featured. These results often precede journal publication and represent the most current research. The principal aim of the IFIP series is to encourage education and the dissemination and exchange of information about all aspects of computing.
Hebbian Learning and Negative Feedback Networks
This book is the outcome of a decade’s research into a speci?c architecture and associated learning mechanism for an arti?cial neural network: the - chitecture involves negative feedback and the learning mechanism is simple Hebbian learning. The research began with my own thesis at the University of Strathclyde, Scotland, under Professor Douglas McGregor which culminated with me being awarded a PhD in 1995 [52], the title of which was “Negative Feedback as an Organising Principle for Arti?cial Neural Networks”. Naturally enough, having established this theme, when I began to sup- vise PhD students of my own, we continued to develop this concept and this book owes much to the research and theses of these students at the Applied Computational Intelligence Research Unit in the University of Paisley . All of Chapters 3 to 8 deal with single stream arti?cial neural networks.
Hands-on question answering systems with BERT : Applications in neural networks and natural language processing
Begins with an overview of the technology landscape behind BERT. It takes you through the basics of NLP, including natural language understanding with tokenization, stemming, and lemmatization, and bag of words. Next, you’ll look at neural networks for NLP starting with its variants such as recurrent neural networks, encoders and decoders, bi-directional encoders and decoders, and transformer models. Along the way, you’ll cover word embedding and their types along with the basics of BERT. After this solid foundation, you’ll be ready to take a deep dive into BERT algorithms such as masked language models and next sentence prediction. You’ll see different BERT variations followed by a hands-on example of a question answering system. You will: Examine the fundamentals of word embeddings / Apply neural networks and BERT for various NLP tasks / Develop a question-answering system from scratch / Train question-answering systems for your own data
Handbook of Nature-Inspired and Innovative Computing : Integrating Classical Models with Emerging Technologies
This comprehensive handbook, the first of its kind to address the connection between nature-inspired and traditional computational paradigms, is a repository of case studies dealing with different problems in computing and solutions to these problems based on nature-inspired paradigms. The "Handbook of Nature-Inspired and Innovative Computing: Integrating Classical Models with Emerging Technologies" is an essential compilation of models, methods, and algorithms for researchers, professionals, and advanced-level students working in all areas of computer science, IT, biocomputing, and network engineering.
Handbook of Geometric Computing : Applications in Pattern Recognition, Computer Vision, Neuralcomputing, and Robotics
Many computer scientists, engineers, applied mathematicians, and physicists use geometry theory and geometric computing methods in the design of perception-action systems, intelligent autonomous systems, and man-machine interfaces. This handbook brings together the most recent advances in the application of geometric computing for building such systems, with contributions from leading experts in the important fields of neuroscience, neural networks, image processing, pattern recognition, computer vision, uncertainty in geometric computations, conformal computational geometry, computer graphics and visualization, medical imagery, geometry and robotics, and reaching and motion planning. For the first time, the various methods are presented in a comprehensive, unified manner.
