Multilayer neural networks trained with the back-propagation algorithm constitute the best example of a successful gradient based learning technique. Given an appropriate network architecture, gradient-based learning algorithms can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters, with minimal preprocessing. This paper reviews various methods applied to handwritten character recognition and compares them on a standard handwritten digit recognition task. Convolutional neural networks, which are specifically designed to deal with the variability of 2D shapes, are shown to outperform all other techniques. Real-life document recognition systems are composed of multiple modules including field extraction, segmentation recognition, and language modeling. A new learning paradigm, called graph transformer networks (GTN), allows such multimodule systems to be trained globally using gradient-based methods so as to minimize an overall performance measure. Two systems for online handwriting recognition are described. Experiments demonstrate the advantage of global training, and the flexibility of graph transformer networks. A graph transformer network for reading a bank cheque is also described. It uses convolutional neural network character recognizers combined with global training techniques to provide record accuracy on business and personal cheques. It is deployed commercially and reads several million cheques per day.

Gradient-based learning applied to document recognition

A new heuristic approach for minimizing possibly nonlinear and non-differentiable continuous space functions is presented. By means of an extensive testbed it is demonstrated that the new method converges faster and with more certainty than many other acclaimed global optimization methods. The new method requires few control variables, is robust, easy to use, and lends itself very well to parallel computation.

/pdf/differential-evolution-a-simple-and-efficient-heuristic-for-4vrb5o5ldc.pdf

Differential Evolution – A Simple and Efficient Heuristic for Global Optimization over Continuous Spaces

Deposits of clastic carbonate-dominated (calciclastic) sedimentary slope systems in the rock record have been identified mostly as linearly-consistent carbonate apron deposits, even though most ancient clastic carbonate slope deposits fit the submarine fan systems better. Calciclastic submarine fans are consequently rarely described and are poorly understood. Subsequently, very little is known especially in mud-dominated calciclastic submarine fan systems. Presented in this study are a sedimentological core and petrographic characterisation of samples from eleven boreholes from the Lower Carboniferous of Bowland Basin (Northwest England) that reveals a >250 m thick calciturbidite complex deposited in a calciclastic submarine fan setting. Seven facies are recognised from core and thin section characterisation and are grouped into three carbonate turbidite sequences. They include: 1) Calciturbidites, comprising mostly of highto low-density, wavy-laminated bioclast-rich facies; 2) low-density densite mudstones which are characterised by planar laminated and unlaminated muddominated facies; and 3) Calcidebrites which are muddy or hyper-concentrated debrisflow deposits occurring as poorly-sorted, chaotic, mud-supported floatstones. These

Phd by thesis

In this paper we present a new data structure for representing Boolean functions and an associated set of manipulation algorithms. Functions are represented by directed, acyclic graphs in a manner similar to the representations introduced by Lee [1] and Akers [2], but with further restrictions on the ordering of decision variables in the graph. Although a function requires, in the worst case, a graph of size exponential in the number of arguments, many of the functions encountered in typical applications have a more reasonable representation. Our algorithms have time complexity proportional to the sizes of the graphs being operated on, and hence are quite efficient as long as the graphs do not grow too large. We present experimental results from applying these algorithms to problems in logic design verification that demonstrate the practicality of our approach.

/pdf/graph-based-algorithms-for-boolean-function-manipulation-2u3osq5jc0.pdf

Graph-Based Algorithms for Boolean Function Manipulation

Our growing dependence on increasingly complex computer and software systems necessitates the development of formalisms, techniques, and tools for assessing functional properties of these systems. One such technique that has emerged in the last twenty years is model checking, which systematically (and automatically) checks whether a model of a given system satisfies a desired property such as deadlock freedom, invariants, and request-response properties. This automated technique for verification and debugging has developed into a mature and widely used approach with many applications. Principles of Model Checking offers a comprehensive introduction to model checking that is not only a text suitable for classroom use but also a valuable reference for researchers and practitioners in the field. The book begins with the basic principles for modeling concurrent and communicating systems, introduces different classes of properties (including safety and liveness), presents the notion of fairness, and provides automata-based algorithms for these properties. It introduces the temporal logics LTL and CTL, compares them, and covers algorithms for verifying these logics, discussing real-time systems as well as systems subject to random phenomena. Separate chapters treat such efficiency-improving techniques as abstraction and symbolic manipulation. The book includes an extensive set of examples (most of which run through several chapters) and a complete set of basic results accompanied by detailed proofs. Each chapter concludes with a summary, bibliographic notes, and an extensive list of exercises of both practical and theoretical nature.

/pdf/principles-of-model-checking-249iimickz.pdf

Principles of Model Checking

A. Richard Newton was larger than life in the eyes of the ones who had the fortune of meeting him. His outlook on life was so different, innovative, and refreshing that one could not avoid being enthralled by his ideas long after parting ways. In this paper, I remember him both as a wonderful human being and as an old and dearest friend. It is not easy for me to do justice to the great contributions that he made to the EDA community and to the world in general. I begin with my own rendition of his accomplishments and his biography decorated with comments from students and colleagues. The body of the paper is about his most significant speeches, which are the best witnesses of his vision and legacy. His own words are so eloquent and convincing that any editing would dilute the message. I will first quote excerpts from his DAC key note address of 1995 and conclude with his unabridged presentation in Berkeley about "the future of the future."

Remembering Richard [A. Richard Newton]

We introduce a new approach to performance analysis of DSP-kernel software, based on high-level abstractions, called implicit cache simulation. The method can take into account any kind of instruction cache as well as code allocation effects. We show that no loss of estimation accuracy is implied by the proposed abstractions. Moreover the speed of the method is such that it can be efficiently used as a system-level design tool. We compare implicit cache simulation with the trace-driven simulation approach, commonly used in industry. Experimental results show that our method is 4 times faster in the average and up to 11 times faster than trace-driven simulation.

Analysis of DSP-kernel software by implicit cache simulation

In this paper, we address the problem of Engineering Change in a non-deterministic finite state machine framework. We are given a deterministic implementation FSM, and a non-deterministic specification FSM, such that the implementation does not meet the specification. The problem consists of controlling the implementation FSM in such a way that for all possible sequences of external inputs, the generated outputs are allowed in the specification. We propose a new formalism for the Engineering Change problem which is applicable to non-deterministic specifications. We use the notion of Simulation Relations from the theory of concurrent systems, to develop this new formalism. Our method is cast in the form of a simulation of the implementation by the specification. We prove the necessary and sufficient condition for the existence of a solution to the problem. We also provide an algorithm to obtain all possible solutions under this setting. We have implemented this algorithm, using implicit state enumeration and Reduced Ordered Binary Decision Diagrams (ROBDDs). An important feature of our method is that the algorithm gives us a solution which is correct by construction, and accordingly we do not need to perform a separate verification step in the design.

An Engineering Change Methodology Using Simulation Relations.

We extend the notion of bisimulation to Kripke structures with fairness. We define equivalences that preserve fairness and are akin to bisimulation. Specifically we define an equivalence and show that it is complete in the sense that it is the coarsest equivalence that preserves the logic CTL* interpreted with respect to the fair paths. We show that the addition of fairness might cause two Kripke structures, which can be distinguished by a CTL* formula, to become indistinguishable by any CTL formula. We also define another weaker equivalence that is the weakest equivalence preserving CTL interpreted on the fair paths. As a consequence of our proof, we also obtain characterizations of states in the fair structure in terms of CTL* and CTL formulae.

Alberto Sangiovanni-Vincentelli

Papers

Remembering Richard [A. Richard Newton]

Analysis of DSP-kernel software by implicit cache simulation

An Engineering Change Methodology Using Simulation Relations.

Equivalences for Fair Kripke Structures.

IEEE GLOBECOM 2009 Symposiums Program