Yasubumi Sakakibara

On case-based learnability of languages

Case-based reasoning is deemed an important technology to alleviate the bottleneck of knowledge acquisition in Artificial Intelligence (AI). In case-based reasoning, knowledge is represented in the form of particular cases with an appropriate similarity measure rather than any form of rules. The case-based reasoning paradigm adopts the view that an Al system is dynamically changing during its life-cycle which immediately leads to learning considerations.Within the present paper, we investigate the problem of case-based learning of indexable classes of formal languages. Prior to learning considerations, we study the problem of case-based representability and show that every indexable class is case-based representable with respect to a fixed similarity measure. Next, we investigate several models of case-based learning and systematically analyze their strengths as well as their limitations. Finally, the general approach to case-based learnability of indexable classes of formal languages is prototypically applied to so-called containmet decision lists, since they seem particularly tailored to case-based knowledge processing.

Text classification and keyword extraction by learning decision trees

Summary form only given. The authors propose a completely new approach to the problem of text classification and automatic keyword extraction by using machine learning techniques. They introduce a class of representations for classifying text data based on decision trees, and present an algorithm for learning it inductively. The algorithm does not need any natural language processing technique, and is robust to noisy data. It is shown that the learning algorithm can be used for automatic extraction of keywords for text retrieval and automatic text categorization. Some experimental results on the use of the algorithm are reported.<<ETX>>

Simple recurrent networks as generalized hidden Markov models with distributed representations

Proposes simple recurrent neural networks as probabilistic models for representing and predicting time-sequences. The proposed model has the advantage of providing forecasts that consist of probability densities instead of single guesses of future values. It turns out that the model can be viewed as a generalized hidden Markov model with a distributed representation. The authors devise an efficient learning algorithm for estimating the parameters of the model using dynamic programming. The authors present some very preliminary simulation results to demonstrate the potential capabilities of the model. The present analysis provides a new probabilistic formulation of learning in simple recurrent networks.

Learning Languages by Collecting Cases and Tuning Parameters

We investigate the problem of case-based learning of formal languages. Case-based reasoning and learning is a currently booming area of artificial intelligence. The formal framework for case-based learning of languages has recently been developed by [JL93] in an inductive inference manner.

A machine learning approach to knowledge acquisitions from text databases

The rapid growth of data in large databases, such as text databases and scientific databases, requires efficient computer methods for automating analyses of the data with the goal of acquiring knowledges or making discoveries. Because the analyses of data are generally so expensive, most parts in databases remains as raw, unanalyzed primary data. Technology from machine learning (ML) will offer efficient tools for the intelligent analyses of the data using generalization ability. Generalization is an important ability specific to inductive learning that will predict unseen data with high accuracy based on learned concepts from training examples. In this article, we apply ML to text‐database analyses and knowledge acquisitions from text databases. We propose a completely new approach to the problem of text classification and extracting keywords by using ML techniques. We introduce a class of representations for classifying text data based on decision trees; (i.e., decision trees over attributes on strings)...

Knowledge acquisitions from large databases using machine learning techniques

The rapid growth of data in large databases such as text database, scientific database requires efficient computer methods for automating analyses of the data with the goal of acquiring knowledges or making discoveries. Since the analyses of data are generally so expensive, most parts in databases remains as raw, unanalyzed, primary data. Technology from machine learning theory will offer efficient tools for the intelligent analysis using “generalization” ability. Generalization is an important ability specific to inductive learning which will predict unseen data with high accuracy based on learned concepts from training examples. We will demonstrate the effectiveness of our approach where generalization ability is applied to predicting and analyzing primary data and extracting knowledges from database by presenting some our results on text database analysis and biological sequence analysis.