Showing papers on "Algorithmic learning theory published in 1982"
01 Jul 1982
TL;DR: A simple model that serves to generate a taxonomy of learning systems is presented and the explication and clarification of four methods of learning single concepts are explained.
Abstract: : The main results of the report are: (a) a simple model that serves to generate a taxonomy of learning systems, (b) the explication and clarification of four methods of learning single concepts, (c) some understanding of the underlying causes of the credit-assignment problem (and possible solutions), and (d) some identification of open research problems and areas that have received little attention. The report is structured as a set of articles. Seven of the articles present the main problems and issues in learning research, while the remaining fifteen articles describe particular learning systems that have been developed.
122 citations
TL;DR: The purpose of the present note is to expose a limitation in the Gold definition of language identification, and thus to raise doubts about the learnability condition that is based upon it.
44 citations
TL;DR: It is found that several precise senses of “ideal machine” are considered within the context of formal learning theory, and generally negative results are provided concerning the existence of ideal learning-machines in the senses considered.
18 citations
Proceedings Article•
18 Aug 1982TL;DR: A technique for learning new words that uses expectations generated by the context and an ISA hierarchy to guide the inference process.
Abstract: A technique for learning new words is discussed. The technique uses expectations generated by the context and an ISA hierarchy to guide the inference process. The learning process uses the context of several independent occurrences of the word to converge on its meaning.
4 citations
01 Jan 1982
TL;DR: This chapter contains sections titled: Section Contents, Representation is the Key to Understanding Learning, representation is the key to Understanding Language, representation and Understanding Human Intelligence.
Abstract: This chapter contains sections titled: Section Contents, Representation is the Key to Understanding Learning, Representation is the Key to Understanding Language, Representation and Understanding Human Intelligence
3 citations
01 Jan 1982
TL;DR: A review of methods of enumerating elementary cycles and circuits is presented, and a geometric view of circuit generation is introduced making use of the properties of dual graphs.
Abstract: A review of methods of enumerating elementary cycles and circuits is presented. For the directed planar graph, a geometric view of circuit generation is introduced making use of the properties of dual graphs. Given the set of elementary cycles or circuits, a particular algorithm is recommended to generate all simple circuits. A simple example accompanies each of the methods discussed. Some methods of reducing the size of the graph but maintaining all circuits are introduced. Worst-case bounds on computational time and space are also given. The problem of enumerating elementary circuits whose cost is less than a certain fixed cost is solved by modifying an existing algorithm. The cost of a circuit is the sum of the cost of the arcs forming the circuit where arc costs are not restricted to be positive. Applications of circuits with particular properties are suggested. Thesis Supervisor: Robert W. Simpson Title: Professor of Aeronautics and Astronautics
2 citations
TL;DR: The concept of Organized Learning is defined, and some random models are presented, and the Algoritmes for the different models are compared.
1 citations
TL;DR: A sample of an integrated learning model is presented, based on Pascual-Leone's theory of constructive operators, and exemplary postulates are developed from the learning model and a theorem is derived from the postulates.
Abstract: Types of instructional theory are defined and a brief review of literature given. A sample of an integrated learning model is presented, based on Pascual-Leone's theory of constructive operators: then, exemplary postulates are developed from the learning model and a theorem is derived from the postulates. The implications of the theorem are discussed in relation to instructional practice, models of learning, and future theory development.
1 citations