Springer (India) Pvt. Ltd., 2017. — 216 p. — (Cognitive Systems Monographs 31) — ISBN: 8132237013
The advent of cheap electronic sensors, cloud computing, IoT, smart devices, mobile computing platforms, driverless cars, drones, etc., has led to generation of enormous amounts of data. Some characteristics central to this big data are its asynchronous and non-standardized nature. The vast amount of data by itself is of less value; however, the ability to effectively and efficiently process it in real-time leading to meaningful patterns, trends, and interpretation is the real treasure trove. Several upcoming unconventional (non-Von Neumann) computing paradigms, where memory (storage) and processing are not isolated tasks in themselves or rather memory is intelligent, offer promising capabilities to this problem of massive non-synchronous, non-standardized data treatment. Techniques such as software artificial neural networks (ANNs), artificial intelligence (AI), and machine learning (ML) have been proving their mettle in fields as diverse as autonomous navigation, to robotics to analytics since a while. However the full potential of these computing paradigms can only be realized when they are directly implemented on dedicated low-power, compact, reconfigurable, programming-free hardware. Contents Hardware Spiking Artificial Neurons, Their Response Function, and Noises Synaptic Plasticity with Memristive Nanodevices Neuromemristive Systems: A Circuit Design Perspective Memristor-Based Platforms: A Comparison Between Continous-Time and Discrete-Time Cellular Neural Networks Reinterpretation of Magnetic Tunnel Junctions as Stochastic Memristive Devices Multiple Binary OxRAMs as Synapses for Convolutional Neural Networks Nonvolatile Memory Crossbar Arrays for Non-von Neumann Computing Novel Biomimetic Si Devices for Neuromorphic Computing Architecture Exploiting Variability in Resistive Memory Devices for Cognitive Systems Theoretical Analysis of Spike-Timing-Dependent Plasticity Learning with Memristive Devices
Чтобы скачать этот файл зарегистрируйтесь и/или войдите на сайт используя форму сверху.