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

Conformational analysis is the problem of finding all minimal energy three-dimensional configurations of molecules. Cyclic structures are of particular interest. An efficient algorithm based on a purely geometric approach that generates feasible configurations very efficiently is presented thus making full conformational analysis possible even for fairly large cyclic structures.

/pdf/chain-closure-a-problem-in-molecular-cad-4ujtfvgzdy.pdf

Chain Closure: A Problem in Molecular CAD

http://www.computer.org/csdl/mags/dt/2002/06/d6120.pdf

The Context for Platform-based Design

As the complexity of embedded systems rapidly increases in terms of both scale and functionality, there has been a strong interest in design languages and methodologies that facilitate the use of formal methods. These languages and methodologies are mostly based on a synchronous paradigm that, while satisfies the need for formalization, often results in an inefficient implementation requiring substantial overhead when compared to approaches that do not enforce synchronicity on the execution platform. Therefore, the interest is high for techniques that on one hand, maintain the formal properties of synchronous models, and on the other hand, enable the use of asynchronous and distributed execution platforms with little overhead. In this paper, we propose an approach for efficient distribution of Triggered Synchronous Block Diagrams (SBDs) on asynchronous platforms while preserving the correct semantics. Compared to previous work that utilizes trigger elimination, our approach aims to reduce the unnecessary communication overhead and thus improve the efficiency of the implementation. We consider both general Triggered SBDs where the values of triggers are dynamically computed, as well as Timed SBDs where triggers are statically known and usually specified by (period, initial phase) pairs.

Efficient distribution of Triggered Synchronous Block Diagrams on asynchronous platforms

ESPRESSO-II receives as its inputs J and D, cube covers of the on-set and the don’t-care set of an incompletely specified Boolean function ff. Optionally, it can accept input J and Rx, cube covers of the on- and off-sets. It returns as its output a “minimized” cover. As discussed in Chapter 1, the objectives of ESPRESSO-II are to minimize: 


NPT: the number of product terms in the cover;


NLI: the number of literals (non-2’s) in the input parts of the cover;


NLO: the number of literals in the output parts.

Alberto Sangiovanni-Vincentelli

Papers

Chain Closure: A Problem in Molecular CAD

The Context for Platform-based Design

Efficient distribution of Triggered Synchronous Block Diagrams on asynchronous platforms

The Espresso-II Minimization Loop and Algorithms

Hard real-time development environments