the Academic NEST

Jan Romportl, Eva Zackova, Jozef Kelemen ... 219 pages - Publisher: Springer; (August, 2014) ... Language: English - ISBN-10: 3319096672 - ISBN-13: 978-3319096674

This book is an edited collection of chapters based on the papers presented at the conference “Beyond AI: Artificial Dreams” held in Pilsen in November 2012. The aim of the conference was to question deep-rooted ideas of artificial intelligence and cast critical reflection on methods standing at its foundations. Artificial Dreams epitomize our controversial quest for non-biological intelligence and therefore the contributors of this book tried to fully exploit such a controversy in their respective chapters, which resulted in an interdisciplinary dialogue between experts from engineering, natural sciences and humanities. While pursuing the Artificial Dreams, it has become clear that it is still more and more difficult to draw a clear divide between human and machine. And therefore this book tries to portrait such an image of what lies beyond artificial intelligence: we can see the disappearing human-machine divide, a very important phenomenon of nowadays technological society, the phenomenon which is often uncritically praised, or hypocritically condemned. And so this phenomenon found its place in the subtitle of the whole volume as well as in the title of the chapter of Kevin Warwick, one of the keynote speakers at “Beyond AI: Artificial Dreams”.

The topics in this course come from an analysis of real requirements in data scientist job listings from the biggest tech employers. We'll cover the machine learning, AI, and data mining techniques real employers are looking for, including: Deep Learning / Neural Networks (MLP's, CNN's, RNN's) with TensorFlow and Keras + Sentiment analysis + Image recognition and classification + Regression analysis + K-Means Clustering + Principal Component Analysis + Train/Test and cross validation + Bayesian Methods + Decision Trees and Random Forests + Multivariate Regression + Multi-Level Models + Support Vector Machines + Reinforcement Learning + Collaborative Filtering + K-Nearest Neighbor + Bias/Variance Tradeoff + Ensemble Learning + Term Frequency / Inverse Document Frequency + Experimental Design and A/B Tests.

Mauro Castelli, L. Sekanina, M. Zhang, S. Cagnoni, P. García-Sánchez ... 323 pages - Publisher: Springer; (April, 2018) ... Language: English - ISBN-10: 3319775529 - ISBN-13: 978-3319775524 ...

This book constitutes the refereed proceedings of the 21st European Conference on Genetic Programming, EuroGP 2018, held in Parma, Italy, in April 2018, co-located with the Evo* 2018 events, EvoCOP, EvoMUSART, and EvoApplications. The 11 revised full papers presented together with 8 poster papers were carefully reviewed and selected from 36 submissions. The wide range of topics in this volume reflects the current state of research in the field. Thus, we see topics and applications including analysis of feature importance for metabolomics, semantic methods, evolution of boolean networks, generation of redundant features, ensembles of GP models, automatic design of grammatical representations, GP and neuroevolution, visual reinforcement learning, evolution of deep neural networks, evolution of graphs, and scheduling in heterogeneous networks.

Giuseppe Ciaburro, Balaji Venkateswaran ... 270 pages - Publisher: Packt Publishing; (September, 2017) ... Language: English - ISBN-10: 1788397878 - ISBN-13: 978-1788397872 ...

Neural networks are one of the most fascinating machine learning models for solving complex computational problems efficiently. Neural networks are used to solve wide range of problems in different areas of AI and machine learning. This book explains the niche aspects of neural networking and provides you with foundation to get started with advanced topics. The book begins with neural network design using the neural net package, then you'll build a solid foundation knowledge of how a neural network learns from data, and the principles behind it. This book covers various types of neural network including recurrent neural networks and convoluted neural networks. You will not only learn how to train neural networks, but will also explore generalization of these networks. Later we will delve into combining different neural network models and work with the real-world use cases. By the end of this book, you will learn to implement neural network models in your applications with the help of practical examples in the book.

S. Chakraverty, Susmita Mall ... 157 pages - Publisher: CRC Press; (July, 2017) ... Language: English - ASIN: B0744Q3RW2 by Amazon.

Differential equations play a vital role in the fields of engineering and science. Problems in engineering and science can be modeled using ordinary or partial differential equations. Analytical solutions of differential equations may not be obtained easily, so numerical methods have been developed to handle them. Machine intelligence methods, such as Artificial Neural Networks (ANN), are being used to solve differential equations, and these methods are presented in Artificial Neural Networks for Engineers and Scientists: Solving Ordinary Differential Equations. This book shows how computation of differential equation becomes faster once the ANN model is properly developed and applied.

Li Deng, Dong Yu ... 212 pages - Publisher: Now Publishers; (June, 2014) ... Language: English - ISBN-10: 1601988141 - ISBN-13: 978-1601988140 ...

Deep Learning: Methods and Applications provides an overview of general deep learning methodology and its applications to a variety of signal and information processing tasks. The application areas are chosen with the following three criteria in mind: (1) expertise or knowledge of the authors; (2) the application areas that have already been transformed by the successful use of deep learning technology, such as speech recognition and computer vision; and (3) the application areas that have the potential to be impacted significantly by deep learning and that have been benefitting from recent research efforts, including natural language and text processing, information retrieval, and multimodal information processing empowered by multi-task deep learning. Deep Learning: Methods and Applications is a timely and important book for researchers and students with an interest in deep learning methodology and its applications in signal and information processing.

Amir Hossein Gandomi, Xin-She Yang, Siamak Talatahari, Amir Hossein Alavi ... 568 pages - Publisher: Elsevier; (February, 2013) ... Language: English - ISBN-10: 0123983649 - ISBN-13: 978-0123983640.

Due to an ever-decreasing supply in raw materials and stringent constraints on conventional energy sources, demand for lightweight, efficient and low-cost structures has become crucially important in modern engineering design. This requires engineers to search for optimal and robust design options to address design problems that are commonly large in scale and highly nonlinear, making finding solutions challenging. In the past two decades, metaheuristic algorithms have shown promising power, efficiency and versatility in solving these difficult optimization problems. This book examines the latest developments of metaheuristics and their applications in structural engineering, construction engineering and earthquake engineering, offering practical case studies as examples to demonstrate real-world applications. Topics cover a range of areas within engineering, including big bang-big crunch approach, genetic algorithms, genetic programming, harmony search, swarm intelligence and some other metaheuristic methods. Case studies include structural identification, vibration analysis and control, topology optimization, transport infrastructure design, design of reinforced concrete, performance-based design of structures and smart pavement management. With its wide range of everyday problems and solutions, Metaheursitic Applications in Structures and Infrastructures can serve as a supplementary text for design courses and computation in engineering as well as a reference for researchers and engineers in metaheuristics, optimization in civil engineering and computational intelligence. * Review of the latest development of metaheuristics in engineering. * Detailed algorithm descriptions with focus on practical implementation. * Uses practical case studies as examples and applications.

A Boltzmann machine is a network of symmetrically connected, neuron-like units that make stochastic decisions about whether to be on or off. Boltzmann machines have a simple learning algorithm that allows them to discover interesting features that represent complex regularities in the training data. The learning algorithm is very slow in networks with many layers of feature detectors, but it is fast in "restricted Boltzmann machines" that have a single layer of feature detectors. Many hidden layers can be learned efficiently by composing restricted Boltzmann machines, using the feature activations of one as the training data for the next. Boltzmann machines are used to solve two quite different computational problems. For a search problem, the weights on the connections are fixed and are used to represent a cost function. The stochastic dynamics of a Boltzmann machine then allow it to sample binary state vectors that have low values of the cost function. For a learning problem, the Boltzmann machine is shown a set of binary data vectors and it must learn to generate these vectors with high probability. To do this, it must find weights on the connections so that, relative to other possible binary vectors, the data vectors have low values of the cost function. To solve a learning problem, Boltzmann machines make many small updates to their weights, and each update requires them to solve many different search problems.

A recurrent neural network (RNN) is a type of advanced artificial neural network (ANN) that involves directed cycles in memory. One aspect of recurrent neural networks is the ability to build on earlier types of networks with fixed-size input vectors and output vectors. The use of recurrent neural networks are often related to deep learning and the use of sequences to evolve models that simulate the neural activity in the human brain. In terms of practical application, RNNs have been an active area of focus for many professionals for uses like image processing, language processing, and even models that add characters to text one at a time. By playing around with these text generation models, scientists have been able to produce samples that look a lot like different kinds of human writing – for example, modern investment op-eds, or classical Shakespeare plays. The RNN has been able to generate text results that demonstrate the ability to learn English from scratch, or from very limited programming inputs. Many examples of using RNNs produce text that is not grammatically correct. The idea is that a large number of these experiments and systems need additional supports to really become useful – but they do demonstrate amazing artificial intelligence power to model the human generation of language.

Convolutional networks (CNNs) are deep artificial neural networks that can be used to classify images (name what they see), cluster them by similarity (photo search), and perform object recognition within scenes. They are algorithms that can identify faces, individuals, street signs, eggplants, platypuses and many other aspects of visual data. Convolutional networks perform optical character recognition (OCR) to digitize text and make natural-language processing possible on analog and hand-written documents, where the images are symbols to be transcribed. CNNs can also be applied to sound when it is represented visually as a spectrogram. More recently, convolutional networks have been applied directly to text analytics as well as graph data with graph convolutional networks. The efficacy of convolutional nets (ConvNets or CNNs) in image recognition is one of the main reasons why the world has woken up to the efficacy of deep learning. They are powering major advances in machine vision, which has obvious applications for self-driving cars, robotics, drones, security, medical diagnoses, and treatments for the visually impaired.

Neural networks are a set of algorithms, modeled loosely after the human brain, that are designed to recognize patterns. They interpret sensory data through a kind of machine perception, labeling or clustering raw input. The patterns they recognize are numerical, contained in vectors, into which all real-world data, be it images, sound, text or time series, must be translated. Neural networks help us cluster and classify. You can think of them as a clustering and classification layer on top of data you store and manage. They help to group unlabeled data according to similarities among the example inputs, and they classify data when they have a labeled dataset to train on. (To be more precise, neural networks extract features that are fed to other algorithms for clustering and classification; so you can think of deep neural networks as components of larger machine-learning applications involving algorithms for reinforcement learning, classification and regression.)

Max Tegmark ... 384 pages - Publisher: Knopf; (August, 2017) ... Language: English - ISBN-10: 1101946598 - ISBN-13: 978-1101946596 ... 

Gayle Cain ... 229 pages - Publisher: Nova Science Pub.; (January, 2017) ... Language: English - ISBN-10: 1634859642 - ISBN-13: 978-1634859646 ...

This current book provides new research on artificial neural networks (ANNs). Topics discussed include the application of ANNs in chemistry and chemical engineering fields; the application of ANNs in the prediction of biodiesel fuel properties from fatty acid constituents; the use of ANNs for solar radiation estimation; the use of in silico methods to design and evaluate skin UV filters; a practical model based on the multilayer perceptron neural network (MLP) approach to predict the milling tool flank wear in a regular cut, as well as entry cut and exit cut, of a milling tool; parameter extraction of small-signal and noise models of microwave transistors based on ANNs; and the application of ANNs to deep-learning and predictive analysis in semantic TCM telemedicine systems.

Rajendra Akerkar, Priti Srinivas Sajja ... 272 pages - Publisher: Springer; 1st edition (October, 2016) ... Language: English - ISBN-10: 3319292056 - ISBN-13: 978-3319292052 ...

This textbook provides readers with the tools, techniques and cases required to excel with modern artificial intelligence methods. These embrace the family of neural networks, fuzzy systems and evolutionary computing in addition to other fields within machine learning, and will help in identifying, visualizing, classifying and analyzing data to support business decisions. The authors, discuss advantages and drawbacks of different approaches, and present a sound foundation for the reader to design and implement data analytic solutions for real‐world applications in an intelligent manner. Intelligent Techniques for Data Science also provides real-world cases of extracting value from data in various domains such as retail, health, aviation, telecommunication and tourism.

Luis Rabelo,‎ Sayli Bhide,‎ Edgar Gutierrez ... 350 pages - Publisher: Nova Science; (February, 2018) ... Language: English - ISBN-10: 1536126772 - ISBN-13: 978-1536126778.

After decades of basic research and more promises than impressive applications, artificial intelligence (AI) is starting to deliver benefits. Organizations around the world have been realizing that there are substantial performance gains and increases in productivity for the use of AI and predictive analytics techniques. Their use is bringing a new era of breakthrough innovation and opportunities. This book, compiles research insights and applications in diverse areas such as manufacturing, supply chain management, pricing, autonomous vehicles, healthcare, ecommerce, and aeronautics. Using classical and advanced tools in AI such as deep learning, particle swarm optimization, support vector machines and genetic programming among others. This is a very distinctive book which discusses important applications using a variety of paradigms from AI and outlines some of the research to be performed. The work supersedes similar books that do not cover as diversified a set of sophisticated applications. The authors present a comprehensive and articulated view of recent developments, identifies the applications gap by quoting from the experience of experts, and details suggested research areas. Artificial Intelligence: Advances in Research and Applications guides the reader through an intuitive understanding of the methodologies and tools for building and modeling intelligent systems. The book's coverage is broad, starting with clustering techniques with unsupervised ensemble learning, where the optimal combination strategy of individual partitions is robust in comparison to the selection of an algorithmic clustering pool. The book discusses how the use of AI can allow for productivity development and other benefits not just for businesses, but also for economies. Finally, you can find an interesting investigation of the "transhuman" dimension of AI. (Nova)

Josh Patterson, Adam Gibson ... 532 pages - Publisher: O'Reilly Media; 1st edition (August, 2017) - Language: English - ISBN-10: 1491914254 - ISBN-13: 978-1491914250 ...

Jorge Magalhães-Mendes, David Greiner ... 127 pages - Publisher: Springer; 1st edition (November, 2016) ... Language: English - ISBN-10: 3319373218 - ISBN-13: 978-3319373218 ...

This book focuses on civil and structural engineering and construction management applications. The contributions constitute modified, extended and improved versions of research presented at the minisymposium organized by the editors at the ECCOMAS conference on this topic in Barcelona 2014.

Xin-She Yang ... 330 pages - Publisher: Springer; 1st edition (October, 2017) ... Language: English - ISBN-10: 3319676687 - ISBN-13: 978-3319676685 ...

This book reviews the state-of-the-art developments in nature-inspired algorithms and their applications in various disciplines, ranging from feature selection and engineering design optimization to scheduling and vehicle routing. It introduces each algorithm and its implementation with case studies as well as extensive literature reviews, and also includes self-contained chapters featuring theoretical analyses, such as convergence analysis and no-free-lunch theorems so as to provide insights into the current nature-inspired optimization algorithms. Topics include ant colony optimization, the bat algorithm, B-spline curve fitting, cuckoo search, feature selection, economic load dispatch, the firefly algorithm, the flower pollination algorithm, knapsack problem, octonian and quaternion representations, particle swarm optimization, scheduling, wireless networks, vehicle routing with time windows, and maximally different alternatives. This timely book serves as a practical guide and reference resource for students, researchers and professionals.

Petia Koprinkova-Hristova, Valeri Mladenov, Nikola K. Kasabov ... 488 pages - Publisher: Springer; (September, 2014) ... Language: English - ISBN-10: 3319099027 - ISBN-13: 978-3319099026 ...

The book reports on the latest theories on artificial neural networks, with a special emphasis on bio-neuroinformatics methods. It includes twenty-three papers selected from among the best contributions on bio-neuroinformatics-related issues, which were presented at the International Conference on Artificial Neural Networks, held in Sofia, Bulgaria, on September 10-13, 2013 (ICANN 2013). The book covers a broad range of topics concerning the theory and applications of artificial neural networks, including recurrent neural networks, super-Turing computation and reservoir computing, double-layer vector perceptrons, nonnegative matrix factorization, bio-inspired models of cell communities, Gestalt laws, embodied theory of language understanding, saccadic gaze shifts and memory formation, and new training algorithms for Deep Boltzmann Machines, as well as dynamic neural networks and kernel machines. It also reports on new approaches to reinforcement learning, optimal control of discrete time-delay systems, new algorithms for prototype selection, and group structure discovering. Moreover, the book discusses one-class support vector machines for pattern recognition, handwritten digit recognition, time series forecasting and classification, and anomaly identification in data analytics and automated data analysis. By presenting the state-of-the-art and discussing the current challenges in the fields of artificial neural networks, bioinformatics and neuroinformatics, the book is intended to promote the implementation of new methods and improvement of existing ones, and to support advanced students, researchers and professionals in their daily efforts to identify, understand and solve a number of open questions in these fields.