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

Thunderbird: a complete standard cell layout system.

The articles in this special issue provides an overview of and a perspective on the evolution of electronic design automation (EDA), and offers a perspective on some of the principal avenues of future development.

Design Automation of Electronic Systems: Past Accomplishments and Challenges Ahead [Scanning the Issue]

In this paper a “direct” noise analysis approach for mixedmode systems is presented with experimental results compared with results from the traditional Monte Carlo approach. The direct approach computes noise effects by performing arithmetic on moments of distribution functions that characterize electronic noise. One key advantage of this approach is its ability to compute low error probabilities. From experimental results, it is shown that very low order moments, such as secondorder, are sufficient for a good estimate of noise effects.

Behavioral simulation for noise in mixed-mode sampled-data systems

We propose an efficient design flow for the automatic synthesis of Networkon-Chip (NOC) topologies. The specification of the problem is given as a netlist of IP cores and their communication requirements. Each IP is characterized by its area. A communication constraint is denoted by its source and destination IP and a minimum bandwidth requirement. Together with the specification, the users provides a percentage of the chip area that they want to allocate for the communication network. Then, given the clock period of the network (that we assume to be synchronous), and a target technology, the proposed design flow explores the entire topology space and returns an optimal NOC where each router has a position and a routing table assigned. We consider two optimality criteria: power consumption and power delay product. Our design flow, which is based on an approximation algorithm, is efficient and highlights the delicate trade-off balance between cost of communication and cost of switching.

Synthesis of Low Power NOC Topologies under Bandwidth Constraints

Microscopic traffic simulation has become an important tool to investigate traffic efficiency and road safety. In order to produce meaningful results, driver behaviour models need to be carefully calibrated to represent real world conditions. If this type of simulations are to be used to evaluate safety features of traffic, on top of macroscopic relationships such as the speed-density diagram, they should also adequately represent the average risk of accidents occurring on the road. In this paper, we present a two-stage computationally feasible multi-objective calibration process. The first stage performs a parameter sensitivity analysis to select only parameters with considerable effect on the respective objective functions. The second stage employs a multi-objective genetic algorithm utilizing only few influential parameters that produces a front of Pareto optimal solutions with respect to the conflicting objective functions. Compared to traditional methods which focus on only one objective while sacrificing the accuracy of the other, our method achieves a high degree of realism for both traffic flow and average risk.

Alberto Sangiovanni-Vincentelli

Papers

Thunderbird: a complete standard cell layout system.

Design Automation of Electronic Systems: Past Accomplishments and Challenges Ahead [Scanning the Issue]

Behavioral simulation for noise in mixed-mode sampled-data systems

Synthesis of Low Power NOC Topologies under Bandwidth Constraints

Multi-Objective Calibration of Microscopic Traffic Simulation for Highway Traffic Safety