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

: This paper focuses on the challenges of modeling cyber-physical systems that arise from the intrinsic heterogeneity, concurrency, and sensitivity to timing of such systems. It uses a portion of an aircraft vehicle management systems (VMS), specifically the fuel management subsystem, to illustrate the challenges and then discusses technologies that at least partially address the challenges. Specific technologies described include hybrid system modeling and simulation, concurrent and heterogeneous models of computation, the use of domain-specific ontologies to enhance modularity, and the joint modeling of functionality and implementation architectures.

/pdf/addressing-modeling-challenges-in-cyber-physical-systems-ncryi0d53f.pdf

Addressing Modeling Challenges in Cyber-Physical Systems

Binary Decision Diagrams (BDDs) are a data structure frequently used to represent complex Boolean functions in formal verification algorithms. An efficient heuristic algorithm for dynamically reducing the size of large reduced ordered BDDs by optimally reordering small windows of consecutive variables is presented. The algorithms have been fully integrated into the Berkeley and Carnegie Mellon BDD packages in such a way that the current variable order dynamically changes and is completely transparent to the user. Dynamic reordering significantly reduces the memory required for BDD-based verification algorithms, thus permitting the verification of significantly more complex systems than was previously possible. The algorithms exhibit a smooth tradeoff between CPU time and reduction in BDD size for almost all BDDs tested. >

Dynamic variable reordering for BDD minimization

Contents. List of Figures. List of Tables. Preface. Acknowledgments. Introduction Sunil P Khatri. 1. Introduction. 2. Validating Deep Sub-Micron Effects. 3. VLSI Layout Fabrics. 4. Fabric I - Fabric Cell Based Design. 5. Fabric 3 - Network of PLA Based Design. 6. Wire Removal in a Network of PLAS. 7. Conclusions and Future Directions. Appendices. Index.

Cross-talk noise immune VLSI design using regular layout fabrics

We present a framework to systematically analyze convolutional neural networks (CNNs) used in classification of cars in autonomous vehicles. Our analysis procedure comprises an image generator that produces synthetic pictures by sampling in a lower dimension image modification subspace and a suite of visualization tools. The image generator produces images which can be used to test the CNN and hence expose its vulnerabilities. The presented framework can be used to extract insights of the CNN classifier, compare across classification models, or generate training and validation datasets.

Systematic Testing of Convolutional Neural Networks for Autonomous Driving

A well-defined methodology for mapping the constraints on a set of critical coupling capacitances into constraints in the vertical-constraint (VC) graph of a channel is presented. The approach involves directing undirected edges, adding directed edges, and increasing the weights of edges in the VC graph in order to meet crossover constraints between orthogonal segments and adjacency constraints between parallel segments while attempting to cause minimum increase in the channel height due to the constraints. Use is made of shield nets when necessary. A formal description of the conditions under which the crossover and the adjacency constraints are satisfied is provided and used to construct the appropriate mapping algorithms. The problem of imposing matching constraints on the routing parasitics in a channel with lateral symmetry is addressed. It is observed that perfect matching is not possible for a matched pair of nets with intersecting horizontal spans. A technique to achieve almost perfect mirror symmetry is presented for such pairs of nets. >

Alberto Sangiovanni-Vincentelli

Papers

Addressing Modeling Challenges in Cyber-Physical Systems

Dynamic variable reordering for BDD minimization

Cross-talk noise immune VLSI design using regular layout fabrics

Systematic Testing of Convolutional Neural Networks for Autonomous Driving

Constraint-based channel routing for analog and mixed analog/digital circuits