IBM

About: IBM is a company organization based out in Armonk, New York, United States. It is known for research contribution in the topics: Layer (electronics) & Cache. The organization has 134567 authors who have published 253905 publications receiving 7458795 citations. The organization is also known as: International Business Machines Corporation & Big Blue.

Convolutional networks for fast, energy-efficient neuromorphic computing

Abstract: Deep networks are now able to achieve human-level performance on a broad spectrum of recognition tasks. Independently, neuromorphic computing has now demonstrated unprecedented energy-efficiency through a new chip architecture based on spiking neurons, low precision synapses, and a scalable communication network. Here, we demonstrate that neuromorphic computing, despite its novel architectural primitives, can implement deep convolution networks that (i) approach state-of-the-art classification accuracy across eight standard datasets encompassing vision and speech, (ii) perform inference while preserving the hardware’s underlying energy-efficiency and high throughput, running on the aforementioned datasets at between 1,200 and 2,600 frames/s and using between 25 and 275 mW (effectively >6,000 frames/s per Watt), and (iii) can be specified and trained using backpropagation with the same ease-of-use as contemporary deep learning. This approach allows the algorithmic power of deep learning to be merged with the efficiency of neuromorphic processors, bringing the promise of embedded, intelligent, brain-inspired computing one step closer.

Document analysis system

Abstract: This paper outlines the requirements and components for a proposed Document Analysis System, which assists a user in encoding printed documents for computer processing. Several critical functions have been investigated and the technical approaches are discussed. The first is the segmentation and classification of digitized printed documents into regions of text and images. A nonlinear, run-length smoothing algorithm has been used for this purpose. By using the regular features of text lines, a linear adaptive classification scheme discriminates text regions from others. The second technique studied is an adaptive approach to the recognition of the hundreds of font styles and sizes that can occur on printed documents. A preclassifier is constructed during the input process and used to speed up a well-known pattern-matching method for clustering characters from an arbitrary print source into a small sample of prototypes. Experimental results are included.

Efficient and Secure Source Authentication for Multicast.

Abstract: One of the main challenges of securing multicast communicationis source authentication,or enabling receivers of multicast data to verify that the received data originated with the claimed source and was not modified enroute. The problem becomes more complex in common settings where other receivers of the data are not trusted, and where lost packets are not retransmitted. Several source authentication schemes for multicast have been suggested in the past, but none of these schemes is satisfactorily efficient in all prominent parameters. We recently proposed a very efficient scheme, TESLA, that is based on initial loose time synchronization between the sender and the receivers, followed by delayed release of keys by the sender. This paper proposes several substantial modifications and improvements to TESLA. One modification allows receivers to authenticate most packets as soon as they arrive (whereas TESLArequires buffering packets at the receiver side, and provides delayed authentication only). Other modifications improve the scalability of the scheme, reduce the space overhead for multiple instances, increase its resistance to denial-of-service attacks, and more.

Siloxane Polymers for High-Resolution, High-Accuracy Soft Lithography

Abstract: We report the formulation of siloxane polymers for high-resolution, high-accuracy stamps for soft lithography. With this technique, a molecular, polymeric, or liquid ink is applied to the surface of a stamp and then transferred by conformal contact to a substrate. Stamps for this technique are usually made of a commercial siloxane elastomer with appropriate mechanical properties to achieve conformal contact but are incapable of printing accurate, submicrometer patterns. To formulate better stamp polymers, we used models of rubber-like elasticity as guidelines. Poly(dimethylsiloxane) networks were prepared from vinyl and hydrosilane end-linked polymers and vinyl and hydrosilane copolymers, with varying mass between cross-links and junction functionality. The polymer formulations were characterized by strain at break as well as compression modulus and surface hardness measurements. This resulted in the identification of bimodal polymer networks having mechanical properties that allow the replication of high...