Cryptosystem designers frequently assume that secrets will be manipulated in closed, reliable computing environments. Unfortunately, actual computers and microchips leak information about the operations they process. This paper examines specific methods for analyzing power consumption measurements to find secret keys from tamper resistant devices. We also discuss approaches for building cryptosystems that can operate securely in existing hardware that leaks information.

/pdf/differential-power-analysis-4t7fjmuc7b.pdf

Differential Power Analysis

This monograph 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 experiencing research growth, including natural language and text processing, information retrieval, and multimodal information processing empowered by multi-task deep learning.

/pdf/deep-learning-methods-and-applications-5cyi610sjz.pdf

Deep Learning: Methods and Applications

This ebook is the first authorized digital version of Kernighan and Ritchie's 1988 classic, The C Programming Language (2nd Ed.). One of the best-selling programming books published in the last fifty years, "K&R" has been called everything from the "bible" to "a landmark in computer science" and it has influenced generations of programmers. Available now for all leading ebook platforms, this concise and beautifully written text is a "must-have" reference for every serious programmers digital library.

As modestly described by the authors in the Preface to the First Edition, this "is not an introductory programming manual; it assumes some familiarity with basic programming concepts like variables, assignment statements, loops, and functions. Nonetheless, a novice programmer should be able to read along and pick up the language, although access to a more knowledgeable colleague will help."

The C programming language

Recently, the hybrid deep neural network (DNN)- hidden Markov model (HMM) has been shown to significantly improve speech recognition performance over the conventional Gaussian mixture model (GMM)-HMM. The performance improvement is partially attributed to the ability of the DNN to model complex correlations in speech features. In this paper, we show that further error rate reduction can be obtained by using convolutional neural networks (CNNs). We first present a concise description of the basic CNN and explain how it can be used for speech recognition. We further propose a limited-weight-sharing scheme that can better model speech features. The special structure such as local connectivity, weight sharing, and pooling in CNNs exhibits some degree of invariance to small shifts of speech features along the frequency axis, which is important to deal with speaker and environment variations. Experimental results show that CNNs reduce the error rate by 6%-10% compared with DNNs on the TIMIT phone recognition and the voice search large vocabulary speech recognition tasks.

/pdf/convolutional-neural-networks-for-speech-recognition-59lskxzlgf.pdf

Convolutional neural networks for speech recognition

From the Publisher:
Connectionist Speech Recognition: A Hybrid Approach describes the theory and implementation of a method to incorporate neural network approaches into state-of-the-art continuous speech recognition systems based on Hidden Markov Models (HMMs) to improve their performance. In this framework, neural networks (and in particular, multilayer perceptrons or MLPs) have been restricted to well-defined subtasks of the whole system, i.e., HMM emission probability estimation and feature extraction. The book describes a successful five year international collaboration between the authors. The lessons learned form a case study that demonstrates how hybrid systems can be developed to combine neural networks with more traditional statistical approaches. The book illustrates both the advantages and limitations of neural networks in the framework of a statistical system. Using standard databases and comparing with some conventional approaches, it is shown that MLP probability estimation can improve recognition performance. Other approaches are discussed, though there is no such unequivocal experimental result for these methods. Connectionist Speech Recognition: A Hybrid Approach is of use to anyone intending to use neural networks for speech recognition or within the framework provided by an existing successful statistical approach. This includes research and development groups working in the field of speech recognition, both with standard and neural network approaches, as well as other pattern recognition and/or neural network researchers. This book is also suitable as a text for advanced courses on neural networks or speech processing.

Connectionist Speech Recognition: A Hybrid Approach

Neural networks (NNs), as processors of time-sequence patterns, have been successfully applied to several speaker dependent speech recognition systems. They can be efficiently implemented by a pipelined architecture. In this paper, the authors explore its window structure as a computation component in the architecture. Two types of windows, parallel and serial data flow window, and their computation units with both feedforward and feedback paths are developed. The implementations of the windows are easily matched to the VLSI medium. Examples of applications to the NNs and performance analysis are given to illustrate effectiveness of the proposed window computation. >

http://ieeexplore.ieee.org/iel2/3013/8562/00374993.pdf

Window structure and computation of neural networks for speech recognition

BiCMOS technology offers enhanced performance compared to CMOS at 5 V power supply voltage. Many high-speed BiCMOS SRAMs, gate arrays, ASICs, etc. have been fabricated [1]. In this chapter, we present a variety of BiCMOS logic circuits suitable for 3.3 and sub-3.3 V. The potential gates for digital applications are identified. The chapter starts with the introduction of the conventional BiCMOS (totem-pole) gate which is used in 5 V applications. The degradation of this gate, with supply voltage scaling, is demonstrated. In Section 5.2, we introduce the BiNMOS family suitable for low-voltage applications. Other logic families, for low power supply voltage operation, are discussed in Section 5.3. Low-voltage digital applications of BiCMOS are identified. The reader is referred to BiCMOS books [2, 3] to get more familiar with BiCMOS circuits.

Low-Voltage VLSI BiCMOS Circuit Design

In recent years, there has been a great deal of research activity in artificial neural networks (ANN) in the area of simulation and hardware implementations [1, 2, 3, 4, 5, 6]. Because of the special features offered by ANNs, such as the capability to learn from examples, adaptation, parallelism, fault tolerance and noise resistance, they have been applied to a number of real-world problems including image and speech processing [3,6, 7, 8, 9]. To enhance the impact of ANNs and broaden the area of applications, it is imperative that ANNs benefit from the state-of-the-art VLSI and ULSI implementation technologies. Because these technologies are basically a digital implementation medium, ANNs must be adapted to an all-digital implementation approach. To illustrate this thesis, the research work reported in this paper offers a practical example of adapting an ANN model to an all-digital VLSI implementation.

An All-Digital VLSI ANN

This paper presents a method for modeling substrate coupling. It also derives closed-form expressions for evaluating coupling elements between two device contacts. Using these expressions, we develop a method for extracting substrate coupling elements in a multi-contact structure. A comparison between our technique and another from the literature for a multi-contact scenario demonstrates the efficiency of our technique.

http://ieeexplore.ieee.org/iel5/7324/19798/00916435.pdf

A semi-analytical quasi-static approach for substrate coupling modeling in VLSI circuits

A methodology is presented for the selection of analog hardware components for the VLSI implementation of the backpropagation learning algorithm. The methodology makes use of a combination of theoretical analysis of error due to analog hardware non-idealities, as well as a procedure for modeling of the behaviour of these non-idealities. The theoretical analysis provides upper bounds on the errors for successful learning as well as for successful recognition of unknown patterns after learning has been completed. The modeling procedure helps to translate the errors due to hardware non-idealities to a form suitable for the theoretical analysis procedure. The bounds derived from the theoretical analysis are verified by simulating the backpropagation algorithm for a sample application, with the errors contained in it. The theoretical bounds are found to agree with the simulation results. >

Mohamed I. Elmasry

Papers

Window structure and computation of neural networks for speech recognition

Low-Voltage VLSI BiCMOS Circuit Design

An All-Digital VLSI ANN

A semi-analytical quasi-static approach for substrate coupling modeling in VLSI circuits

A methodology for selection of analog hardware for back-propagation algorithm implementation