This book presents the necessary and essential backgrounds of fuzzy set theory and linear programming, particularly a broad range of common Fuzzy Linear Programming (FLP) models and related, convenient solution techniques. These models and methods belong to three common classes of fuzzy linear programming, namely: (i) FLP problems in which all coefficients are fuzzy numbers, (ii) FLP problems in which the right-hand-side vectors and the decision variables are fuzzy numbers, and (iii) FLP problems in which the cost coefficients, the right-hand-side vectors and the decision variables are fuzzy numbers. The book essentially generalizes the well-known solution algorithms used in linear programming to the fuzzy environment. Accordingly, it can be used not only as a textbook, teaching material or reference book for undergraduate and graduate students in courses on applied mathematics, computer science, management science, industrial engineering, artificial intelligence, fuzzy information processes, and operations research, but can also serve as a reference book for researchers in these fields, especially those engaged in optimization and soft computing. For textbook purposes, it also includes simple and illustrative examples to help readers who are new to the field.

This book offers a rigorous mathematical analysis of fuzzy geometrical ideas. It demonstrates the use of fuzzy points for interpreting an imprecise location and for representing an imprecise line by a fuzzy line. Further, it shows that a fuzzy circle can be used to represent a circle when its description is not known precisely, and that fuzzy conic sections can be used to describe imprecise conic sections. Moreover, it discusses fundamental notions on fuzzy geometry, including the concepts of fuzzy line segment and fuzzy distance, as well as key fuzzy operations, and includes several diagrams and numerical illustrations to make the topic more understandable. The book fills an important gap in the literature, providing the first comprehensive reference guide on the fuzzy mathematics of imprecise image subsets and imprecise geometrical objects. Mainly intended for researchers active in fuzzy optimization, it also includes chapters relevant for those working on fuzzy image processing and pattern recognition. Furthermore, it is a valuable resource for beginners interested in basic operations on fuzzy numbers, and can be used in university courses on fuzzy geometry, dealing with imprecise locations, imprecise lines, imprecise circles, and imprecise conic sections.

Data-driven computational neuroscience facilitates the transformation of data into insights into the structure and functions of the brain. This introduction for researchers and graduate students is the first in-depth, comprehensive treatment of statistical and machine learning methods for neuroscience. The methods are demonstrated through case studies of real problems to empower readers to build their own solutions. The book covers a wide variety of methods, including supervised classification with non-probabilistic models (nearest-neighbors, classification trees, rule induction, artificial neural networks and support vector machines) and probabilistic models (discriminant analysis, logistic regression and Bayesian network classifiers), meta-classifiers, multi-dimensional classifiers and feature subset selection methods. Other parts of the book are devoted to association discovery with probabilistic graphical models (Bayesian networks and Markov networks) and spatial statistics with point processes (complete spatial randomness and cluster, regular and Gibbs processes). Cellular, structural, functional, medical and behavioral neuroscience levels are considered.

This book focuses on the fields of fuzzy logic and metaheuristic algorithms, particularly the harmony search algorithm and fuzzy control. There are currently several types of metaheuristics used to solve a range of real-world of problems, and these metaheuristics contain parameters that are usually fixed throughout the iterations. However, a number of techniques are also available that dynamically adjust the parameters of an algorithm, such as probabilistic fuzzy logic. This book proposes a method of addressing the problem of parameter adaptation in the original harmony search algorithm using type-1, interval type-2 and generalized type-2 fuzzy logic. The authors applied this methodology to the resolution of problems of classical benchmark mathematical functions, CEC 2015, CEC2017 functions and to the optimization of various fuzzy logic control cases, and tested the method using six benchmark control problems - four of the Mamdani type: the problem of filling a water tank, the problem of controlling the temperature of a shower, the problem of controlling the trajectory of an autonomous mobile robot and the problem of controlling the speed of an engine; and two of the Sugeno type: the problem of controlling the balance of a bar and ball, and the problem of controlling control the balance of an inverted pendulum. When the interval type-2 fuzzy logic system is used to model the behavior of the systems, the results show better stabilization because the uncertainty analysis is better. As such, the authors conclude that the proposed method, based on fuzzy systems, fuzzy controllers and the harmony search optimization algorithm, improves the behavior of complex control plants.

This book describes new theories and applications of artificial neural networks, with a special focus on addressing problems in neuroscience, biology and biophysics and cognitive research. It covers a wide range of methods and technologies, including deep neural networks, large-scale neural models, brain-computer interface, signal processing methods, as well as models of perception, studies on emotion recognition, self-organization and many more. The book includes both selected and invited papers presented at the XX International Conference on Neuroinformatics, held in Moscow, Russia on October 8-12, 2018.

This book aims at providing an overview of state-of-the-art in both the theory and methods of intuitionistic fuzzy logic, partial differential equations and numerical methods in informatics. It covers topics such as fuzzy intuitionistic Hilbert spaces, intuitionistic fuzzy differential equations, fuzzy intuitionistic metric spaces, and numerical methods for differential equations. It reports on applications such as fuzzy real time scheduling, intelligent control, diagnostics and time series prediction. Chapters were carefully selected among contributions presented at the second edition of the International Conference on Intuitionistic Fuzzy Sets and Mathematical Science, ICIFSMAS, held on April 11-13, 2018, at Al Akhawayn University of Ifrane, in Morocco.

Visualize and build deep learning models with 3D data using PyTorch3D and other Python frameworks to conquer real-world application challenges with ease Key Features Understand 3D data processing with rendering, PyTorch optimization, and heterogeneous batching Implement differentiable rendering concepts with practical examples Discover how you can ease your work with the latest 3D deep learning techniques using PyTorch3D Book DescriptionWith this hands-on guide to 3D deep learning, developers working with 3D computer vision will be able to put their knowledge to work and get up and running in no time. Complete with step-by-step explanations of essential concepts and practical examples, this book lets you explore and gain a thorough understanding of state-of-the-art 3D deep learning. You'll see how to use PyTorch3D for basic 3D mesh and point cloud data processing, including loading and saving ply and obj files, projecting 3D points into camera coordination using perspective camera models or orthographic camera models, rendering point clouds and meshes to images, and much more. As you implement some of the latest 3D deep learning algorithms, such as differential rendering, Nerf, synsin, and mesh RCNN, you'll realize how coding for these deep learning models becomes easier using the PyTorch3D library. By the end of this deep learning book, you'll be ready to implement your own 3D deep learning models confidently. What you will learn Develop 3D computer vision models for interacting with the environment Get to grips with 3D data handling with point clouds, meshes, ply, and obj file format Work with 3D geometry, camera models, and coordination and convert between them Understand concepts of rendering, shading, and more with ease Implement differential rendering for many 3D deep learning models Advanced state-of-the-art 3D deep learning models like Nerf, synsin, mesh RCNN Who this book is forThis book is for beginner to intermediate-level machine learning practitioners, data scientists, ML engineers, and DL engineers who are looking to become well-versed with computer vision techniques using 3D data.

This book presents an extension of the aggregation operator of the generalized interval type-2 Sugeno integral using generalized type-2 fuzzy logic. This extension enables it to handle higher levels of uncertainty when adding any number of sources and types of information in a wide variety of decision-making applications. The authors also demonstrate that the extended aggregation operator offers better performance than other traditional or extended operators. The book is a valuables reference resource for students and researchers working on theory and applications of fuzzy logic in various areas of application where decision making is performed under high levels of uncertainty, such as pattern recognition, time series prediction, intelligent control and manufacturing.

This book explores recent perspectives on type-2 fuzzy sets. Written as a tribute to Professor Jerry Mendel for his pioneering works on type-2 fuzzy sets and systems, it covers a wide range of topics, including applications to the Go game, machine learning and pattern recognition, as well as type-2 fuzzy control and intelligent systems. The book is intended as a reference guide for the type-2 fuzzy logic community, yet it aims also at other communities dealing with similar methods and applications.

This book comprises papers on diverse aspects of fuzzy logic, neural networks, and nature-inspired optimization meta-heuristics and their application in various areas such as intelligent control and robotics, pattern recognition, medical diagnosis, time series prediction and optimization of complex problems. The book is organized into seven main parts, each with a collection of papers on a similar subject. The first part presents new concepts and algorithms based on type-2 fuzzy logic for dynamic parameter adaptation in meta-heuristics. The second part discusses network theory and applications, and includes papers describing applications of neural networks in diverse areas, such as time series prediction and pattern recognition. The third part addresses the theory and practice of meta-heuristics in different areas of application, while the fourth part describes diverse fuzzy logic applications in the control area, which can be considered as intelligent controllers. The next two parts explore applications in areas, such as time series prediction, and pattern recognition and new optimization and evolutionary algorithms and their applications respectively. Lastly, the seventh part addresses the design and application of different hybrid intelligent systems.

This book proposes a novel neural architecture, tree-based convolutional neural networks (TBCNNs),for processing tree-structured data. TBCNNsare related to existing convolutional neural networks (CNNs) and recursive neural networks (RNNs), but they combine the merits of both: thanks to their short propagation path, they are as efficient in learning as CNNs; yet they are also as structure-sensitive as RNNs. In this book, readers will also find a comprehensive literature review of related work, detailed descriptions of TBCNNs and their variants, and experiments applied to program analysis and natural language processing tasks. It is also an enjoyable read for all those with a general interest in deep learning.

This book constitutes the refereed proceedings of the 15th International Symposium on Neural Networks, ISNN 2018, held in Minsk, Belarus in June 2018.The 98 revised regular papers presented in this volume were carefully reviewed and selected from 214 submissions. The papers cover many topics of neural network-related research including intelligent control, neurodynamic analysis, bio-signal, bioinformatics and biomedical engineering, clustering, classification, forecasting, models, algorithms, cognitive computation, machine learning, and optimization.

Learn the core concepts of neural networks and discover the different types of neural network, using Unity as your platform. In this book you will start by exploring back propagation and unsupervised neural networks with Unity and C#. You'll then move onto activation functions, such as sigmoid functions, step functions, and so on. The author also explains all the variations of neural networks such as feed forward, recurrent, and radial. Once you've gained the basics, you'll start programming Unity with C#. In this section the author discusses constructing neural networks for unsupervised learning, representing a neural network in terms of data structures in C#, and replicating a neural network in Unity as a simulation. Finally, you'll define back propagation with Unity C#, before compiling your project. What You'll Learn Discover the concepts behind neural networks Work with Unity and C# See the difference between fully connected and convolutional neural networks Master neural network processing for Windows 10 UWP Who This Book Is For Gaming professionals, machine learning and deep learning enthusiasts.

In this book, a methodology for parameter adaptation in meta-heuristic op-timization methods is proposed. This methodology is based on using met-rics about the population of the meta-heuristic methods, to decide through a fuzzy inference system the best parameter values that were carefully se-lected to be adjusted. With this modification of parameters we want to find a better model of the behavior of the optimization method, because with the modification of parameters, these will affect directly the way in which the global or local search are performed.Three different optimization methods were used to verify the improve-ment of the proposed methodology. In this case the optimization methods are: PSO (Particle Swarm Optimization), ACO (Ant Colony Optimization) and GSA (Gravitational Search Algorithm), where some parameters are se-lected to be dynamically adjusted, and these parameters have the most im-pact in the behavior of each optimization method.Simulation results show that the proposed methodology helps to each optimization method in obtaining better results than the results obtained by the original method without parameter adjustment.

This SpringerBrief describes how to build a rigorous end-to-end mathematical framework for deep neural networks. The authors provide tools to represent and describe neural networks, casting previous results in the field in a more natural light. In particular, the authors derive gradient descent algorithms in a unified way for several neural network structures, including multilayer perceptrons, convolutional neural networks, deep autoencoders and recurrent neural networks. Furthermore, the authors developed framework is both more concise and mathematically intuitive than previous representations of neural networks. This SpringerBrief is one step towards unlocking the black box of Deep Learning. The authors believe that this framework will help catalyze further discoveries regarding the mathematical properties of neural networks.This SpringerBrief is accessible not only to researchers, professionals and students working and studying in the field of deep learning, but also to those outside of the neutral network community.

The key component in forecasting demand and consumption of resources in a supply network is an accurate prediction of real-valued time series. Indeed, both service interruptions and resource waste can be reduced with the implementation of an effective forecasting system. Significant research has thus been devoted to the design and development of methodologies for short term load forecasting over the past decades. A class of mathematical models, called Recurrent Neural Networks, are nowadays gaining renewed interest among researchers and they are replacing many practical implementations of the forecasting systems, previously based on static methods. Despite the undeniable expressive power of these architectures, their recurrent nature complicates their understanding and poses challenges in the training procedures. Recently, new important families of recurrent architectures have emerged and their applicability in the context of load forecasting has not been investigated completely yet. This work performs a comparative study on the problem of Short-Term Load Forecast, by using different classes of state-of-the-art Recurrent Neural Networks. The authors test the reviewed models first on controlled synthetic tasks and then on different real datasets, covering important practical cases of study. The text also provides a general overview of the most important architectures and defines guidelines for configuring the recurrent networks to predict real-valued time series.

The six volume set LNCS 10634, LNCS 10635, LNCS 10636, LNCS 10637, LNCS 10638, and LNCS 10639 constitues the proceedings of the 24rd International Conference on Neural Information Processing, ICONIP 2017, held in Guangzhou, China, in November 2017. The 563 full papers presented were carefully reviewed and selected from 856 submissions. The 6 volumes are organized in topical sections on Machine Learning, Reinforcement Learning, Big Data Analysis, Deep Learning, Brain-Computer Interface, Computational Finance, Computer Vision, Neurodynamics, Sensory Perception and Decision Making, Computational Intelligence, Neural Data Analysis, Biomedical Engineering, Emotion and Bayesian Networks, Data Mining, Time-Series Analysis, Social Networks, Bioinformatics, Information Security and Social Cognition, Robotics and Control, Pattern Recognition, Neuromorphic Hardware and Speech Processing.

The two volume set, LNCS 10613 and 10614, constitutes the proceedings of then 26th International Conference on Artificial Neural Networks, ICANN 2017, held in Alghero, Italy, in September 2017. The 128 full papers included in this volume were carefully reviewed and selected from 270 submissions. They were organized in topical sections named: From Perception to Action; From Neurons to Networks; Brain Imaging; Recurrent Neural Networks; Neuromorphic Hardware; Brain Topology and Dynamics; Neural Networks Meet Natural and Environmental Sciences; Convolutional Neural Networks; Games and Strategy; Representation and Classification; Clustering; Learning from Data Streams and Time Series; Image Processing and Medical Applications; Advances in Machine Learning. There are 63 short paper abstracts that are included in the back matter of the volume.

The two volume set, LNCS 10613 and 10614, constitutes the proceedings of then 26th International Conference on Artificial Neural Networks, ICANN 2017, held in Alghero, Italy, in September 2017. The 128 full papers included in this volume were carefully reviewed and selected from 270 submissions. They were organized in topical sections named: From Perception to Action; From Neurons to Networks; Brain Imaging; Recurrent Neural Networks; Neuromorphic Hardware; Brain Topology and Dynamics; Neural Networks Meet Natural and Environmental Sciences; Convolutional Neural Networks; Games and Strategy; Representation and Classification; Clustering; Learning from Data Streams and Time Series; Image Processing and Medical Applications; Advances in Machine Learning. There are 63 short paper abstracts that are included in the back matter of the volume.

In this book a neural network learning method with type-2 fuzzy weight adjustment is proposed. The mathematical analysis of the proposed learning method architecture and the adaptation of type-2 fuzzy weights are presented. The proposed method is based on research of recent methods that handle weight adaptation and especially fuzzy weights.The internal operation of the neuron is changed to work with two internal calculations for the activation function to obtain two results as outputs of the proposed method. Simulation results and a comparative study among monolithic neural networks, neural network with type-1 fuzzy weights and neural network with type-2 fuzzy weights are presented to illustrate the advantages of the proposed method.The proposed approach is based on recent methods that handle adaptation of weights using fuzzy logic of type-1 and type-2. The proposed approach is applied to a cases of prediction for the Mackey-Glass (for o=17) and Dow-Jones time series, and recognition of person with iris biometric measure. In some experiments, noise was applied in different levels to the test data of the Mackey-Glass time series for showing that the type-2 fuzzy backpropagation approach obtains better behavior and tolerance to noise than the other methods.The optimization algorithms that were used are the genetic algorithm and the particle swarm optimization algorithm and the purpose of applying these methods was to find the optimal type-2 fuzzy inference systems for the neural network with type-2 fuzzy weights that permit to obtain the lowest prediction error.

The four volume set LNCS 9489, LNCS 9490, LNCS 9491, and LNCS 9492 constitutes the proceedings of the 22nd International Conference on Neural Information Processing, ICONIP 2015, held in Istanbul, Turkey, in November 2015. The 231 full papers presented were carefully reviewed and selected from 375 submissions. The 4 volumes represent topical sections containing articles on Learning Algorithms and Classification Systems; Artificial Intelligence and Neural Networks: Theory, Design, and Applications; Image and Signal Processing; and Intelligent Social Networks.

This book focuses on identifying the performance challenges involved in computer architectures, optimal configuration settings and analysing their impact on the performance of multi-core architectures. Proposing a power and throughput-aware fuzzy-logic-based reconfiguration for Multi-Processor Systems on Chip (MPSoCs) in both simulation and real-time environments, it is divided into two major parts. The first part deals with the simulation-based power and throughput-aware fuzzy logic reconfiguration for multi-core architectures, presenting the results of a detailed analysis on the factors impacting the power consumption and performance of MPSoCs. In turn, the second part highlights the real-time implementation of fuzzy-logic-based power-efficient reconfigurable multi-core architectures for Intel and Leone3 processors.

The two volume set, LNCS 9886 + 9887, constitutes the proceedings of the 25th International Conference on Artificial Neural Networks, ICANN 2016, held in Barcelona, Spain, in September 2016. The 121 full papers included in this volume were carefully reviewed and selected from 227 submissions. They were organized in topical sections named: from neurons to networks; networks and dynamics; higher nervous functions; neuronal hardware; learning foundations; deep learning; classifications and forecasting; and recognition and navigation. There are 47 short paper abstracts that are included in the back matter of the volume.

The two volume set, LNCS 9886 + 9887, constitutes the proceedings of the 25th International Conference on Artificial Neural Networks, ICANN 2016, held in Barcelona, Spain, in September 2016. The 121 full papers included in this volume were carefully reviewed and selected from 227 submissions. They were organized in topical sections named: from neurons to networks; networks and dynamics; higher nervous functions; neuronal hardware; learning foundations; deep learning; classifications and forecasting; and recognition and navigation. There are 47 short paper abstracts that are included in the back matter of the volume.

This book provides an introduction to fuzzy logic approaches useful in image processing. The authors start by introducing image processing tasks of low and medium level such as thresholding, enhancement, edge detection, morphological filters, and segmentation and shows how fuzzy logic approaches apply. The book is divided into two parts. The first includes vagueness and ambiguity in digital images, fuzzy image processing, fuzzy rule based systems, and fuzzy clustering. The second part includes applications to image processing, image thresholding, color contrast enhancement, edge detection, morphological analysis, and image segmentation. Throughout, they describe image processing algorithms based on fuzzy logic under methodological aspects in addition to applicative aspects. Implementations in java are provided for the various applications.