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

http://www.eecs.ucf.edu/~dcm/Teaching/COT4810-Spring2011/Literature/SensorNetworksSurvey.pdf

Wireless sensor networks: a survey

Networking together hundreds or thousands of cheap microsensor nodes allows users to accurately monitor a remote environment by intelligently combining the data from the individual nodes. These networks require robust wireless communication protocols that are energy efficient and provide low latency. We develop and analyze low-energy adaptive clustering hierarchy (LEACH), a protocol architecture for microsensor networks that combines the ideas of energy-efficient cluster-based routing and media access together with application-specific data aggregation to achieve good performance in terms of system lifetime, latency, and application-perceived quality. LEACH includes a new, distributed cluster formation technique that enables self-organization of large numbers of nodes, algorithms for adapting clusters and rotating cluster head positions to evenly distribute the energy load among all the nodes, and techniques to enable distributed signal processing to save communication resources. Our results show that LEACH can improve system lifetime by an order of magnitude compared with general-purpose multihop approaches.

/pdf/an-application-specific-protocol-architecture-for-wireless-1s7y9fiv40.pdf

An application-specific protocol architecture for wireless microsensor networks

Alhussein Abouzeid Rensselaer Polytechnic Institute Raviraj Adve University of Toronto Dharma Agrawal University of Cincinnati Walid Ahmed Tyco M/A-COM Sonia Aissa University of Quebec, INRSEMT Huseyin Arslan University of South Florida Nallanathan Arumugam National University of Singapore Saewoong Bahk Seoul National University Claus Bauer Dolby Laboratories Brahim Bensaou Hong Kong University of Science and Technology Rick Blum Lehigh University Michael Buehrer Virginia Tech Antonio Capone Politecnico di Milano Javier Gómez Castellanos National University of Mexico Claude Castelluccia INRIA Henry Chan The Hong Kong Polytechnic University Ajit Chaturvedi Indian Institute of Technology Kanpur Jyh-Cheng Chen National Tsing Hua University Yong Huat Chew Institute for Infocomm Research Tricia Chigan Michigan Tech Dong-Ho Cho Korea Advanced Institute of Science and Tech. Jinho Choi University of New South Wales Carlos Cordeiro Philips Research USA Laurie Cuthbert Queen Mary University of London Arek Dadej University of South Australia Sajal Das University of Texas at Arlington Franco Davoli DIST University of Genoa Xiaodai Dong, University of Alberta Hassan El-sallabi Helsinki University of Technology Ozgur Ercetin Sabanci University Elza Erkip Polytechnic University Romano Fantacci University of Florence Frank Fitzek Aalborg University Mario Freire University of Beira Interior Vincent Gaudet University of Alberta Jairo Gutierrez University of Auckland Michael Hadjitheodosiou University of Maryland Zhu Han University of Maryland College Park Christian Hartmann Technische Universitat Munchen Hossam Hassanein Queen's University Soong Boon Hee Nanyang Technological University Paul Ho Simon Fraser University Antonio Iera University "Mediterranea" of Reggio Calabria Markku Juntti University of Oulu Stefan Kaiser DoCoMo Euro-Labs Nei Kato Tohoku University Dongkyun Kim Kyungpook National University Ryuji Kohno Yokohama National University Bhaskar Krishnamachari University of Southern California Giridhar Krishnamurthy Indian Institute of Technology Madras Lutz Lampe University of British Columbia Bjorn Landfeldt The University of Sydney Peter Langendoerfer IHP Microelectronics Technologies Eddie Law Ryerson University in Toronto

Wireless communications

https://www.cs.montana.edu/courses/csci566/Ref/CR-Survey.pdf

NeXt generation/dynamic spectrum access/cognitive radio wireless networks: a survey

Portable computers have soared in popularity over the last few years. Vendors are introducing new models with smaller form factors, longer battery life, communications capabilities and unique user interfaces using pen or audio input.
The design and implementation of a networked user interface architecture using handwriting recognition and speech recognition is explored. Although the user interface was designed for mobile multimedia terminals such as the InfoPad system, it is more generally applicable in any application domain where pen and/or spoken input are preferable to keyboard input.
We examine the kinds of handwriting and speech recognizers needed to provide an effective user interface. There are several aspects to this problem. Firstly, there is the user interaction model which determines where and how the user uses each input modality. Secondly, there is the applications programming model which determines the level of abstraction and the extent of encapsulation of the recognizer's functionality. Thirdly, there is the service provision model which determines whether the recognizer is part of the application or whether it runs as a separate thread or process, or somewhere in between. The latter allows off-loading the recognition computation onto a remote, possibly specialized server and minimizes the impact of compute-intensive recognizers on other applications.
The entire infrastructure for a pen and speech based user interface is described, including a software hidden Markov model based writer-independent hand-print recognizer, a VLSI hidden Markov model based large-vocabulary speaker independent continuous speech recognizer, type servers to handle the new data types and applications that exercise the entire user interface architecture.

Pen and speech recognition in the user interface for mobile multimedia terminals

With the popularity of portable devices such as personal digital assistants and personal communicators, as well as with increasing awareness of the economic and environmen- tal costs of power consumption by desktop computers, energy efficiency has emerged as an important issue in the design of electronic systems. While power efficient ASIC's with dedicated architectures have addressed the energy efficiency issue for niche applications such as DSP, much of the computation continues to be implemented as software running on programmable processors such as microprocessors, microcontrollers, and programmable DSP's. Not only is this true for general purpose computation on personal computers and workstations, but also for portable devices, application-specific systems etc. In fact, firmware and embedded software executing on RISC and DSP processor cores that are embedded in ASIC's has emerged as a leading implemen- tation methodology for speech coding, modem functionality, video compression, communication protocol processing etc. This paper describes architectural techniques for energy efficient implemen- tation of programmable computation, particularly focussing on the computation needed in portable devices where event-driven user interfaces, communication protocols, and signal processing play a dominant role. Two key approaches described here are predictive system shutdown and extended voltage scaling. Results indicate that a large reduction in power consumption can be achieved over current day solutions with little or no loss in system performance.

ystem Shutdown and Other rchitectural Techniques for Energy rogrammable Computation

The InfoPad project was started at UC Berkeley in 1992 to investigatethe issues involved in providing multimedia information accessusing a portable, wireless terminal. It quickly became clear that a keydesign constraint was the energy consumption, which could best beaddressed through an integrated system approach. The project wastherefore organized to address all design levels, including the applicationsand user interface, backbone network protocols, software fordistributed network support, the wireless link, and the pad itselfwhich used a number of low voltage ASIC designs and a processorrunning embedded code. Tools were developed when not available(particularly in support of low energy design), as well as an interfaceto mechanical designers who created a custom injection moldedcase. The wide scope of the project presented a number of uniquechallenges for a research environment and the lessons learn will be presented.

http://www.cecs.uci.edu/~papers/compendium94-03/papers/1997/dac97/pdffiles/19_2.pdf

InfoPad—an experiment in system level design and integration

The degradation of thin gate oxide (∼100A) n and p-channel MOSFETs subjected to the substrate hot carrier injection is discussed. The generation of oxide trapped charges is observed to be sublinearly dependent on the applied oxide field, while the generation of interface trapped charges shows a linear dependence on the applied oxide field. The generation rates are found to be a function of carrier fluence and the oxide field, and are independent of the injection current density. The generation of interface traps correlates well with the mobility and subthreshold current degradation. An oxide field around 5MV/cm is found to be a critical value for accelerating device degradation. There is no significant interface trap generation under substrate hot hole injection for the hole fluence up to 2\times10^{17} /cm2. The threshold voltage shifts decrease with increasing applied substrate bias. Possible mechanisms are discussed to account for the experimental data.

Hot carriers induced degradation in thin gate oxide MOSFETs

With the availability of 7 GHz of unlicensed spectrum around 60 GHz, there is growing interest in using this resource for new consumer applications requiring very high-data-rate wireless transmission. Historically, the cost of the 60 GHz electronics, implemented in compound semiconductor technology, has been prohibitively expensive. A fully integrated CMOS solution has the potential to drastically reduce costs enough to hit consumer price points. System, circuit, and device-level barriers to a low-cost 60 GHz CMOS implementation are described, potential solutions are explored, and remaining challenges are discussed.

Robert W. Brodersen

Papers

Pen and speech recognition in the user interface for mobile multimedia terminals

ystem Shutdown and Other rchitectural Techniques for Energy rogrammable Computation

InfoPad—an experiment in system level design and integration

Hot carriers induced degradation in thin gate oxide MOSFETs

Design Considerations for