Search results for "Reason"
showing 10 items of 526 documents
Optimization problem in inductive inference
1995
Algorithms recognizing to which of n classes some total function belongs are constructed (n > 2). In this construction strategies determining to which of two classes the function belongs are used as subroutines. Upper and lower bounds for number of necessary strategies are obtained in several models: FIN- and EX-identification and EX-identification with limited number of mindchanges. It is proved that in EX-identification it is necessary to use n(n−1)/2 strategies. In FIN-identification [3n/2 − 2] strategies are necessary and sufficient, in EX-identification with one mindchange- n log2n+o(n log2n) strategies.
Predictive and Evolutive Cross-Referencing for Web Textual Sources
2017
International audience; One of the main challenges in the domain of competitive intelligence is to harness important volumes of information from the web, and extract the most valuable pieces of information. As the amount of information available on the web grows rapidly and is very heterogeneous, this process becomes overwhelming for experts. To leverage this challenge, this paper presents a vision for a novel process that performs cross-referencing at web scale. This process uses a focused crawler and a semantic-based classifier to cross-reference textual items without expert intervention, based on Big Data and Semantic Web technologies. The system is described thoroughly, and interests of…
Learning with belief levels
2008
AbstractWe study learning of predicate logics formulas from “elementary facts,” i.e. from the values of the predicates in the given model. Several models of learning are considered, but most of our attention is paid to learning with belief levels. We propose an axiom system which describes what we consider to be a human scientist's natural behavior when trying to explore these elementary facts. It is proved that no such system can be complete. However we believe that our axiom system is “practically” complete. Theorems presented in the paper in some sense confirm our hypothesis.
Systematic reasoning: Formal or postformal cognition?
1995
The focus of this study was to investigate the relationship between formal and postformal systematic metasystematic reasoning. Shayer's (1978) chemicals task and a modified version of Kuhn and Brannock's (1977) plant task were used to measure formal thinking and Commons, Richard, and Kuhn's (1982) multisystem task and balance-beam task to detect postformal reasoning. Subjects were university students from the humanities and social sciences (N=35). For each subject, a composite score was defined by taking into account the highest score in the tasks measuring the same developmental stage. Findings indicated that composite scores of formal and postformal reasoning were significantly correlated…
Self-learning inductive inference machines
1991
Self-knowledge is a concept that is present in several philosophies. In this article, we consider the issue of whether or not a learning algorithm can in some sense possess self-knowledge. The question is answered affirmatively. Self-learning inductive inference algorithms are taken to be those that learn programs for their own algorithms, in addition to other functions. La connaissance de soi est un concept qui se retrouve dans plusieurs philosophies. Dans cet article, les auteurs s'interrogent a savoir si un algorithme d' apprentissage peut dans une certaine mesure posseder la connaissance de soi. lis apportent une reponse positive a cette question. Les algorithmes d'inference inductive a…
Learning formulae from elementary facts
1997
Since the seminal paper by E.M. Gold [Gol67] the computational learning theory community has been presuming that the main problem in the learning theory on the recursion-theoretical level is to restore a grammar from samples of language or a program from its sample computations. However scientists in physics and biology have become accustomed to looking for interesting assertions rather than for a universal theory explaining everything.
Memory limited inductive inference machines
1992
The traditional model of learning in the limit is restricted so as to allow the learning machines only a fixed, finite amount of memory to store input and other data. A class of recursive functions is presented that cannot be learned deterministically by any such machine, but can be learned by a memory limited probabilistic leaning machine with probability 1.
On the duality between mechanistic learners and what it is they learn
1993
All previous work in inductive inference and theoretical machine learning has taken the perspective of looking for a learning algorithm that successfully learns a collection of functions. In this work, we consider the perspective of starting with a set of functions, and considering the collection of learning algorithms that are successful at learning the given functions. Some strong dualities are revealed.
Querying and reasoning over large scale building data sets
2016
International audience; The architectural design and construction domains work on a daily basis with massive amounts of data. Properly managing, exchanging and exploiting these data is an ever ongoing challenge in this domain. This has resulted in large semantic RDF graphs that are to be combined with a significant number of other data sets (building product catalogues, regulation data, geometric point cloud data, simulation data, sensor data), thus making an already huge dataset even larger. Making these big data available at high performance rates and speeds and into the correct (intuitive) formats is therefore an incredibly high challenge in this domain. Yet, hardly any benchmark is avai…
Transformations that preserve learnability
1996
We consider transformations (performed by general recursive operators) mapping recursive functions into recursive functions. These transformations can be considered as mapping sets of recursive functions into sets of recursive functions. A transformation is said to be preserving the identification type I, if the transformation always maps I-identifiable sets into I-identifiable sets.