Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

In this book, innovative research using artificial neural networks (ANNs) is conducted to automate the placement task in analog integrated circuit layout design, by creating a generalized model that can generate valid layouts at push-button speed. Further, it exploits ANNs’ generalization and push-button speed prediction (once fully trained) capabilities, and details the optimal description of the input/output data relation. The description developed here is chiefly reflected in two of the system’s characteristics: the shape of the input data and the minimized loss function. In order to address the latter, abstract and segmented descriptions of both the input data and the objective behavior are developed, which allow the model to identify, in newer scenarios, sub-blocks which can be found in the input data. This approach yields device-level descriptions of the input topology that, for each device, focus on describing its relation to every other device in the topology. By means of these descriptions, an unfamiliar overall topology can be broken down into devices that are subject to the same constraints as a device in one of the training topologies. In the experimental results chapter, the trained ANNs are used to produce a variety of valid placement solutions even beyond the scope of the training/validation sets, demonstrating the model’s effectiveness in terms of identifying common components between newer topologies and reutilizing the acquired knowledge. Lastly, the methodology used can readily adapt to the given problem’s context (high label production cost), resulting in an efficient, inexpensive and fast model. .

Programming --- programmeren (informatica)

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

Programming --- coderen --- Agile --- programmeren (informatica)

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

This book delivers the state of the art in deep learning (DL) methods hybridized with evolutionary computation (EC). Over the last decade, DL has dramatically reformed many domains: computer vision, speech recognition, healthcare, and automatic game playing, to mention only a few. All DL models, using different architectures and algorithms, utilize multiple processing layers for extracting a hierarchy of abstractions of data. Their remarkable successes notwithstanding, these powerful models are facing many challenges, and this book presents the collaborative efforts by researchers in EC to solve some of the problems in DL. EC comprises optimization techniques that are useful when problems are complex or poorly understood, or insufficient information about the problem domain is available. This family of algorithms has proven effective in solving problems with challenging characteristics such as non-convexity, non-linearity, noise, and irregularity, which dampen the performance of most classic optimization schemes. Furthermore, EC has been extensively and successfully applied in artificial neural network (ANN) research —from parameter estimation to structure optimization. Consequently, EC researchers are enthusiastic about applying their arsenal for the design and optimization of deep neural networks (DNN). This book brings together the recent progress in DL research where the focus is particularly on three sub-domains that integrate EC with DL: (1) EC for hyper-parameter optimization in DNN; (2) EC for DNN architecture design; and (3) Deep neuroevolution. The book also presents interesting applications of DL with EC in real-world problems, e.g., malware classification and object detection. Additionally, it covers recent applications of EC in DL, e.g. generative adversarial networks (GAN) training and adversarial attacks. The book aims to prompt and facilitate the research in DL with EC both in theory and in practice.

Programming --- Computer. Automation --- neuronale netwerken --- programmeren (informatica)

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

Pascal Laube presents machine learning approaches for three key problems of reverse engineering of defective structured surfaces: parametrization of curves and surfaces, geometric primitive classification and inpainting of high-resolution textures. The proposed methods aim to improve the reconstruction quality while further automating the process. The contributions demonstrate that machine learning can be a viable part of the CAD reverse engineering pipeline. Contents Machine Learning Methods for Parametrization in Curve and Surface Approximation Classification of Geometric Primitives in Point Clouds Image Inpainting for High-resolution Textures Using CNN Texture Synthesis Target Groups Lecturers and students in the field of machine learning, geometric modeling and information theory Practitioners in the field of machine learning, surface reconstruction and CAD The Author Pascal Laube’s main research interest is the development of machine learning methods for CAD reverse engineering. He is currently developing self-driving cars for an international operating German enterprise in the field of mobility, automotive and industrial technology.

Applied physical engineering --- Programming --- Computer. Automation --- fabrieken --- computers --- programmeren (informatica)

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

This book offers a comprehensible overview of Big Data Preprocessing, which includes a formal description of each problem. It also focuses on the most relevant proposed solutions. This book illustrates actual implementations of algorithms that helps the reader deal with these problems. This book stresses the gap that exists between big, raw data and the requirements of quality data that businesses are demanding. This is called Smart Data, and to achieve Smart Data the preprocessing is a key step, where the imperfections, integration tasks and other processes are carried out to eliminate superfluous information. The authors present the concept of Smart Data through data preprocessing in Big Data scenarios and connect it with the emerging paradigms of IoT and edge computing, where the end points generate Smart Data without completely relying on the cloud. Finally, this book provides some novel areas of study that are gathering a deeper attention on the Big Data preprocessing. Specifically, it considers the relation with Deep Learning (as of a technique that also relies in large volumes of data), the difficulty of finding the appropriate selection and concatenation of preprocessing techniques applied and some other open problems. Practitioners and data scientists who work in this field, and want to introduce themselves to preprocessing in large data volume scenarios will want to purchase this book. Researchers that work in this field, who want to know which algorithms are currently implemented to help their investigations, may also be interested in this book.

Programming --- Information systems --- Computer. Automation --- computers --- programmeren (informatica) --- gegevensanalyse