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) & Signal. 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.

Latent semantic indexing: a probabilistic analysis

Abstract: Latent semantic indexing LSI is an information retrieval technique based on the spectral analysis of the term document matrix whose empirical success had heretofore been without rigorous prediction and explanation We prove that under certain conditions LSI does succeed in capturing the underlying semantics of the corpus and achieves improved retrieval performance We also propose the technique of random projection as a way of speeding up LSI We complement our theorems with encouraging experimental results We also argue that our results may be viewed in a more general framework as a theoretical basis for the use of spectral methods in a wider class of applications such as collaborative ltering

Deep Learning with Limited Numerical Precision

Abstract: Training of large-scale deep neural networks is often constrained by the available computational resources. We study the effect of limited precision data representation and computation on neural network training. Within the context of low-precision fixed-point computations, we observe the rounding scheme to play a crucial role in determining the network's behavior during training. Our results show that deep networks can be trained using only 16-bit wide fixed-point number representation when using stochastic rounding, and incur little to no degradation in the classification accuracy. We also demonstrate an energy-efficient hardware accelerator that implements low-precision fixed-point arithmetic with stochastic rounding.

Parameter and quantile estimation for the generalized pareto distribution

Abstract: The generalized Pareto distribution is a two-parameter distribution that contains uniform, exponential, and Pareto distributions as special cases. It has applications in a number of fields, including reliability studies and the analysis of environmental extreme events. Maximum likelihood estimation of the generalized Pareto distribution has previously been considered in the literature, but we show, using computer simulation, that, unless the sample size is 500 or more, estimators derived by the method of moments or the method of probability-weighted moments are more reliable. We also use computer simulation to assess the accuracy of confidence intervals for the parameters and quantiles of the generalized Pareto distribution.

A relational model of data for large shared data banks

Abstract: Future users of large data banks must be protected from having to know how the data is organized in the machine (the internal representation). A prompting service which supplies such information is not a satisfactory solution. Activities of users at terminals and most application programs should remain unaffected when the internal representation of data is changed and even when some aspects of the external representation are changed. Changes in data representation will often be needed as a result of changes in query, update, and report traffic and natural growth in the types of stored information.Existing noninferential, formatted data systems provide users with tree-structured files or slightly more general network models of the data. In Section 1, inadequacies of these models are discussed. A model based on n-ary relations, a normal form for data base relations, and the concept of a universal data sublanguage are introduced. In Section 2, certain operations on relations (other than logical inference) are discussed and applied to the problems of redundancy and consistency in the user's model.

Quality driven web services composition

Abstract: The process-driven composition of Web services is emerging as a promising approach to integrate business applications within and across organizational boundaries. In this approach, individual Web services are federated into composite Web services whose business logic is expressed as a process model. The tasks of this process model are essentially invocations to functionalities offered by the underlying component services. Usually, several component services are able to execute a given task, although with different levels of pricing and quality. In this paper, we advocate that the selection of component services should be carried out during the execution of a composite service, rather than at design-time. In addition, this selection should consider multiple criteria (e.g., price, duration, reliability), and it should take into account global constraints and preferences set by the user (e.g., budget constraints). Accordingly, the paper proposes a global planning approach to optimally select component services during the execution of a composite service. Service selection is formulated as an optimization problem which can be solved using efficient linear programming methods. Experimental results show that this global planning approach outperforms approaches in which the component services are selected individually for each task in a composite service.