Machine Learning And Non Volatile Memories

This book presents the basics of both NAND flash storage and machine learning, detailing the storage problems the latter can help to solve. At a first sight, machine learning and non-volatile memories seem very far away from each other. Machine learning implies mathematics, algorithms and a lot of computation; non-volatile memories are solid-state devices used to store information, having the amazing capability of retaining the information even without power supply. This book will help the reader understand how these two worlds can work together, bringing a lot of value to each other. In particular, the book covers two main fields of application: analog neural networks (NNs) and solid-state drives (SSDs). After reviewing the basics of machine learning in Chapter 1, Chapter 2 shows how neural networks can mimic the human brain; to accomplish this result, neural networks have to perform a specific computation called vector-by-matrix (VbM) multiplication, which is particularly power hungry. In the digital domain, VbM is implemented by means of logic gates which dictate both the area occupation and the power consumption; the combination of the two poses serious challenges to the hardware scalability, thus limiting the size of the neural network itself, especially in terms of the number of processable inputs and outputs. Non-volatile memories (phase change memories in Chapter 3, resistive memories in Chapter 4, and 3D flash memories in Chapter 5 and Chapter 6) enable the analog implementation of the VbM (also called “neuromorphic architecture”), which can easily beat the equivalent digital implementation in terms of both speed and energy consumption. SSDs and flash memories are strictly coupled together; as 3D flash scales, there is a significant amount of work that has to be done in order to optimize the overall performances of SSDs. Machine learning has emerged as a viable solution in many stages of this process. After introducing the main flash reliability issues, Chapter 7 shows both supervised and un-supervised machine learning techniques that can be applied to NAND. In addition, Chapter 7 deals with algorithms and techniques for a pro-active reliability management of SSDs. Last but not least, the last section of Chapter 7 discusses the next challenge for machine learning in the context of the so-called computational storage. No doubt that machine learning and non-volatile memories can help each other, but we are just at the beginning of the journey; this book helps researchers understand the basics of each field by providing real application examples, hopefully, providing a good starting point for the next level of development.

This book presents the latest techniques for characterization, modeling and design for nano-scale non-volatile memory (NVM) devices. Coverage focuses on fundamental NVM device fabrication and characterization, internal state identification of memristic dynamics with physics modeling, NVM circuit design and hybrid NVM memory system design-space optimization. The authors discuss design methodologies for nano-scale NVM devices from a circuits/systems perspective, including the general foundations for the fundamental memristic dynamics in NVM devices. Coverage includes physical modeling, as well as the development of a platform to explore novel hybrid CMOS and NVM circuit and system design. • Offers readers a systematic and comprehensive treatment of emerging nano-scale non-volatile memory (NVM) devices; • Focuses on the internal state of NVM memristic dynamics, novel NVM readout and memory cell circuit design and hybrid NVM memory system optimization; • Provides both theoretical analysis and practical examples to illustrate design methodologies; • Illustrates design and analysis for recent developments in spin-toque-transfer, domain-wall racetrack and memristors.

Metal Oxides for Non-volatile Memory: Materials, Technology and Applications covers the technology and applications of metal oxides (MOx) in non-volatile memory (NVM) technology. The book addresses all types of NVMs, including floating-gate memories, 3-D memories, charge-trapping memories, quantum-dot memories, resistance switching memories and memristors, Mott memories and transparent memories. Applications of MOx in DRAM technology where they play a crucial role to the DRAM evolution are also addressed. The book offers a broad scope, encompassing discussions of materials properties, deposition methods, design and fabrication, and circuit and system level applications of metal oxides to non-volatile memory. Finally, the book addresses one of the most promising materials that may lead to a solution to the challenges in chip size and capacity for memory technologies, particular for mobile applications and embedded systems. Systematically covers metal oxides materials and their properties with memory technology applications, including floating-gate memory, 3-D memory, memristors, and much more Provides an overview on the most relevant deposition methods, including sputtering, CVD, ALD and MBE Discusses the design and fabrication of metal oxides for wide breadth of non-volatile memory applications from 3-D flash technology, transparent memory and DRAM technology

In recent years, the abundant advantages of quantum physics, quantum dots, quantum wires, quantum wells, and nanocrystals in various applications have attracted considerable scientific attention in the field of nonvolatile memory (NVM). Nanocrystals are the driving elements that have helped nonvolatile flash memory technology reach its distinguished height, but new approaches are still needed to strengthen nanocrystal-based nonvolatile technology for future applications. This book presents comprehensive knowledge on nanocrystal fabrication methods and applications of nanocrystals in baseline NVM and emerging NVM technologies and the chapters are written by experts in the field from all over the globe. The book presents a detailed analysis on nanocrystal-based emerging devices by a high-level researcher in the field. It has a unique chapter especially dedicated to graphene-based flash memory devices, considering the importance of carbon allotropes in future applications. This updated edition covers emerging ferroelectric memory device, which is a technology for the future, and the chapter is contributed by the well-known Ferroelectric Memory Company, Germany. It includes information related to the applications of emerging memories in sensors and the chapter is contributed by Ajou University, South Korea. The book introduces a new chapter for emerging NVM technology in artificial intelligence and the chapter is contributed by University College London, UK. It guides the readers throughout with appropriate illustrations, excellent figures, and references in each chapter. It is a valuable tool for researchers and developers from the fields of electronics, semiconductors, nanotechnology, materials science, and solid-state memories.

Advances in Nonvolatile Memory and Storage Technology, Second Edition, addresses recent developments in the non-volatile memory spectrum, from fundamental understanding, to technological aspects. The book provides up-to-date information on the current memory technologies as related by leading experts in both academia and industry. To reflect the rapidly changing field, many new chapters have been included to feature the latest in RRAM technology, STT-RAM, memristors and more. The new edition describes the emerging technologies including oxide-based ferroelectric memories, MRAM technologies, and 3D memory. Finally, to further widen the discussion on the applications space, neuromorphic computing aspects have been included. This book is a key resource for postgraduate students and academic researchers in physics, materials science and electrical engineering. In addition, it will be a valuable tool for research and development managers concerned with electronics, semiconductors, nanotechnology, solid-state memories, magnetic materials, organic materials and portable electronic devices. Discusses emerging devices and research trends, such as neuromorphic computing and oxide-based ferroelectric memories Provides an overview on developing nonvolatile memory and storage technologies and explores their strengths and weaknesses Examines improvements to flash technology, charge trapping and resistive random access memory

This book presents recent advances towards the goal of enabling efficient implementation of machine learning models on resource-constrained systems, covering different application domains. The focus is on presenting interesting and new use cases of applying machine learning to innovative application domains, exploring the efficient hardware design of efficient machine learning accelerators, memory optimization techniques, illustrating model compression and neural architecture search techniques for energy-efficient and fast execution on resource-constrained hardware platforms, and understanding hardware-software codesign techniques for achieving even greater energy, reliability, and performance benefits.

Exa-scale computing needs to re-examine the existing hardware platform that can support intensive data-oriented computing. Since the main bottleneck is from memory, we aim to develop an energy-efficient in-memory computing platform in this book. First, the models of spin-transfer torque magnetic tunnel junction and racetrack memory are presented. Next, we show that the spintronics could be a candidate for future data-oriented computing for storage, logic, and interconnect. As a result, by utilizing spintronics, in-memory-based computing has been applied for data encryption and machine learning. The implementations of in-memory AES, Simon cipher, as well as interconnect are explained in details. In addition, in-memory-based machine learning and face recognition are also illustrated in this book.

This book explores several problems and their solutions regarding data analysis and prediction for industrial applications. Machine learning is a prominent topic in modern industries: its influence can be felt in many aspects of everyday life, as the world rapidly embraces big data and data analytics. Accordingly, there is a pressing need for novel and innovative algorithms to help us find effective solutions in industrial application areas such as media, healthcare, travel, finance, and retail. In all of these areas, data is the crucial parameter, and the main key to unlocking the value of industry. The book presents a range of intelligent algorithms that can be used to filter useful information in the above-mentioned application areas and efficiently solve particular problems. Its main objective is to raise awareness for this important field among students, researchers, and industrial practitioners.