Optimization is often a question of where one should put one’s money in improving performance. As far as large storage hierarchies go, intuition suggests (and common practice supports) adding as much as is affordable of the fastest technology available. Many cache hierarchy studies have shown that this is often not the optimal approach, and we show that for mass storage hierarchies it always te...

Learning to rank have become a famous problem for document retrieval and other applications. Recently, several machine learning techniques are applied into this task. Ranking SVM, which uses Support Vector Machine (SVM) to perform the problem, is an example. In this paper, we present a novel approach which also based on SVM. We consider the modification of SVM by adding bias term to different r...

In 1982, Sharp launched research into machine translation, English to Japanese. Since then, the company has commercialized a series of machine translation systems, DUET E/J, E/J-II, J/E, and Qt, and most recently has ported the system onto a business-use Japanese word processor "SHOIN" adding a new feature called “phrase-to-phrase translation function.” This is to overview the features of DUET ...

This paper presents English—Hindi transliteration in the NEWS 2009 Machine Transliteration Shared Task adding source context modeling into state-of-the-art log-linear phrase-based statistical machine translation (PB-SMT). Source context features enable us to exploit source similarity in addition to target similarity, as modelled by the language model. We use a memory-based classification framew...

This paper presents English—Hindi transliteration in the NEWS 2009 Machine Transliteration Shared Task adding source context modeling into state-of-the-art log-linear phrase-based statistical machine translation (PB-SMT). Source context features enable us to exploit source similarity in addition to target similarity, as modelled by the language model. We use a memory-based classification framew...

We build Neural Machine Translation (NMT) systems for EnglishHindi,Bengali-Hindi and Gujarati-Hindi with two different units of translation i.e. word and subword and present a comparative study of subword NMT and word level NMT systems, along with strong results and case studies. We train attention-based encoder-decoder model for word level and use Byte Pair Encoding (BPE) in subword NMT for wo...

Is there any potential benefit when training threshold circuits by adding extra layers (depth) to the network? This question is investigated in a powerful recently introduced artificial intelligence system, called the Logarithmic Simulated Annealing (LSA) machine, that combines the Simulated Annealing Algorithm with a Logarithmic cooling schedule and the classical perceptron algorithm. The firs...

selecting an appropriate manufacturing machine is a very important and complex problem for firms, which usually have to deal with both qualitative and quantitative criteria. taking into account the differences among machines in terms of cost, speed, quality and after sale services, type and number of machines are important parameters to consider. therefore, the goal of this paper is to propose ...

Template matching is a widely used technique in many of image processing and machine vision applications. In this paper we propose a new as well as a fast and reliable template matching algorithm which is invariant to Rotation, Scale, Translation and Brightness (RSTB) changes. For this purpose, we adopt the idea of ring projection transform (RPT) of image. In the proposed algorithm, two novel s...

The Transparent Prolog Machine (TPM) provides a vehicle for visualising the execution of Prolog programs in a manner which is faithful to the underlying behaviour of the Prolog interpreter. Although this fidelity is useful for teaching and debugging purposes, it can be inappropriate when a programmer wishes to view a program at a 'higher level', i.e. in terms of data or procedure abstractions w...