Results 1  10
of
509
A Theory Of Inferred Causation
, 1991
"... This paper concerns the empirical basis of causation, and addresses the following issues: 1. the clues that might prompt people to perceive causal relationships in uncontrolled observations. 2. the task of inferring causal models from these clues, and 3. whether the models inferred tell us anything ..."
Abstract

Cited by 254 (38 self)
 Add to MetaCart
useful about the causal mechanisms that underly the observations. We propose a minimalmodel semantics of causation, and show that, contrary to common folklore, genuine causal influences can be distinguished from spurious covariations following standard norms of inductive reasoning. We also establish a
The induction of dynamical recognizers
 Machine Learning
, 1991
"... A higher order recurrent neural network architecture learns to recognize and generate languages after being "trained " on categorized exemplars. Studying these networks from the perspective of dynamical systems yields two interesting discoveries: First, a longitudinal examination of the le ..."
Abstract

Cited by 225 (14 self)
 Add to MetaCart
of the learning process illustrates a new form of mechanical inference: Induction by phase transition. A small weight adjustment causes a "bifurcation" in the limit behavior of the network. This phase transition corresponds to the onset of the network’s capacity for generalizing to arbitrary
Word Learning as Bayesian Inference
 In Proceedings of the 22nd Annual Conference of the Cognitive Science Society
, 2000
"... The authors present a Bayesian framework for understanding how adults and children learn the meanings of words. The theory explains how learners can generalize meaningfully from just one or a few positive examples of a novel word’s referents, by making rational inductive inferences that integrate pr ..."
Abstract

Cited by 175 (33 self)
 Add to MetaCart
The authors present a Bayesian framework for understanding how adults and children learn the meanings of words. The theory explains how learners can generalize meaningfully from just one or a few positive examples of a novel word’s referents, by making rational inductive inferences that integrate
Parsimony hierarchies for inductive inference
 Journal of Symbolic Logic
"... Freivalds defined an acceptable programming system independent criterion for learning programs for functions in which the final programs were required to be both correct and “nearly” minimal size, i.e, within a computable function of being purely minimal size. Kinber showed that this parsimony requ ..."
Abstract

Cited by 3 (1 self)
 Add to MetaCart
requirement on final programs limits learning power. However, in scientific inference, parsimony is considered highly desirable. A limcomputable function is (by definition) one calculable by a total procedure allowed to change its mind finitely many times about its output. Investigated is the possibility
Covariation in natural causal induction
 Psychological Review
, 1992
"... The covariation component of everyday causal inference has been depicted, in both cognitive and social psychology as well as in philosophy, as heterogeneous and prone to biases. The models and biases discussed in these domains are analyzed with respect to focal sets: contextually determined sets of ..."
Abstract

Cited by 122 (6 self)
 Add to MetaCart
indicates that a single normative mechanism—the computation of probabilistic contrasts—underlies this essential component of natural causal induction both in everyday and in scientific situations. We do not perceive the visual world as a twodimensional mosaic of bits of light patches. Instead, these data
Refutable Inductive Inference of Recursive Functions
, 2001
"... Learning of recursive functions refutably informally means that for every recursive function, the learning machine has either to learn this function or to refute it, that is to signal that it is not able to learn it. Three modi of making precise the notion of refuting are considered. We show that ..."
Abstract

Cited by 1 (1 self)
 Add to MetaCart
the refuting ability of the corresponding learning machines comes from and how it can be realized, in general. For learning with anomalies refutably, we show that several results from standard learning without refutation stand refutably. From this we derive some hierarchies for refutable learning. Finally
Two Variations of Inductive Inference of Languages from Positive Data
, 1995
"... The present paper deals with the learnability of indexed families of uniformly recursive languages by single inductive inference machines (abbr. IIM) and teams of IIMs from positive and both positive and negative data. We study the learning power of single IIMs in dependence on the hypothesis space ..."
Abstract

Cited by 4 (3 self)
 Add to MetaCart
and the number of allowed anomalies the synthesized language may have. Our results are fourfold. First, we show that allowing anomalies does not increase the learning power as long as inference from positive and negative data is considered. Second, we establish an infinite hierarchy in the number of allowed
The Communication of Inductive Inferences
 In Weiß, G. (eds) ECAI’96: Selected papers from the Workshop on Distributed Artificial Intelligence Meets Machine Learning, Learning in Multiagent Environments
, 1997
"... Abstract We propose a new approach to communication between agents that perform inductive inference. Consider a community of agents where each agent has a limited view of the overall world. When an agent in this community induces a hypothesis about the world, it necessarily reflects that agent’s par ..."
Abstract

Cited by 16 (3 self)
 Add to MetaCart
Abstract We propose a new approach to communication between agents that perform inductive inference. Consider a community of agents where each agent has a limited view of the overall world. When an agent in this community induces a hypothesis about the world, it necessarily reflects that agent’s
The Use of Planning Critics in Mechanizing Inductive Proofs
 International Conference on Logic Programming and Automated Reasoning  LPAR 92, St. Petersburg, Lecture Notes in Artificial Intelligence No. 624
, 1992
"... Proof plans provide a technique for guiding the search for a proof in the context of tactical style reasoning. We propose an extension to this technique in which failure may be exploited in the search for a proof. This extension is based upon the concept of planning critics. In particular we ill ..."
Abstract

Cited by 61 (12 self)
 Add to MetaCart
illustrate how proof critics may be used to patch proof plans in the domain of inductive proofs. 1 Introduction Proof plans [Bundy 88] guide the search for a proof in the context of tactical style reasoning [Gordon et al 79]. A proof plan contains a tactic together with a proof rationale. The tactic
Inductive Inference of Limiting Programs with Bounded Number of Mind Changes
"... We consider inductive inference of total recursive functions in the case, when produced hypotheses are allowed some nite number of times to change \their mind " about each value of identi able function. Such type of identi cation, which we call inductive inference of limiting programs with ..."
Abstract
 Add to MetaCart
mind changes and the number of anomalies, and relations between classes of functions identi able with di erent probabilities. For the case of probabilistic identi cation we establish probabilistic hierarchies which are quite unusual for EX and BC types of inference. 1
Results 1  10
of
509