Machine Learning: A Guide to Current Research by Tom M. Mitchell, Jaime G. Carbonell, Ryszard S. Michalski

By Tom M. Mitchell, Jaime G. Carbonell, Ryszard S. Michalski

One of the presently so much energetic examine parts inside man made Intelligence is the sector of computer studying. which contains the examine and improvement of computational versions of studying techniques. an incredible objective of analysis during this box is to construct pcs in a position to enhancing their functionality with perform and of buying wisdom on their lonesome. The purpose of this booklet is to supply a picture of this box via a huge. consultant set of simply assimilated brief papers. As such. this booklet is meant to enrich the 2 volumes of computing device studying: a synthetic Intelligence process (Morgan-Kaufman Publishers). which offer a smaller variety of in-depth study papers. all of the seventy seven papers within the current ebook summarizes a present study attempt. and offers references to longer expositions showing somewhere else. those papers conceal a huge variety of subject matters. together with learn on analogy. conceptual clustering. explanation-based generalization. incremental studying. inductive inference. studying apprentice structures. computer discovery. theoretical versions of studying. and functions of desktop studying equipment. a subject matter index is supplied to aid in finding examine relating to particular themes. nearly all of those papers have been accumulated from the individuals on the 3rd overseas laptop studying Workshop. held June 24-26. 1985 at Skytop resort. Skytop. Pennsylvania. whereas the checklist of analysis tasks lined isn't really exhaustive. we think that it presents a consultant sampling of the easiest ongoing paintings within the box. and a special viewpoint on the place the sphere is and the place it's headed.

Show description

Read Online or Download Machine Learning: A Guide to Current Research PDF

Best intelligence & semantics books

Cambrian Intelligence: The Early History of the New AI

This e-book is a suite of the "best" / so much brought up Brooks papers. essentially it covers what's thought of the center of papers that obtained behaviour established robotics rolling. just about all papers have seemed as magazine papers past and this is often basically a handy number of those. For someone engaged on cellular robotics those papers are a needs to.

Recent Advances in AI Planning: 4th European Conference on Planning, ECP'97, Toulouse, France, September 24 - 26, 1997, Proceedings

This booklet constitutes the refereed complaints of the 4th eu convention on making plans, ECP'97, held in Toulouse, France, in September 1997. The 35 revised complete papers offered have been rigorously reviewed and chosen from ninety submissions. the diversity of subject matters coated spans all facets of present man made intelligence making plans, from theoretical and foundational concerns to real making plans of structures and purposes in quite a few parts.

Artificial Intelligence: Its Scope and Limits

This sequence will comprise monographs and collections of stories dedicated to the research and exploration of data, details, and information­ processing platforms of all types, regardless of no matter if human, (other) animal, or laptop. Its scope is meant to span the entire diversity of pursuits from classical difficulties within the philosophy of brain and philosophical psycholo­ gy via matters in cognitive psychology and sociobiology (concerning the psychological features of alternative species) to rules concerning man made in­ telligence and to laptop technology.

Application of Evolutionary Algorithms for Multi-objective Optimization in VLSI and Embedded Systems

This booklet describes how evolutionary algorithms (EA), together with genetic algorithms (GA) and particle swarm optimization (PSO) can be used for fixing multi-objective optimization difficulties within the region of embedded and VLSI approach layout. Many complicated engineering optimization difficulties may be modelled as multi-objective formulations.

Extra resources for Machine Learning: A Guide to Current Research

Example text

We must have a general method of perceiving. encoding. structuring. and retrieving events of different degrees of complexity. For such a purpose. we developed an event memory method reported in [263]. We are investigating a unified cognitive architecture using this event memory [Mozer (this volume)] in which we are building the first prototype versions of a first-words language acquisition module and a simple plan-acquisition module that formulates and acquires plans to handle recurring goals (such as learning to squirrel away food if it is available now.

The entire cycle repeats starting with Step 1. ACKNOWLEDGMENTS We would like to thank the other members of the World Modelers Group (Keith Barnett. Klaus Gross. Pat Langley. Mike Mozer. Alain Rappaport. and Hans Tallis) for their their ideas and comments on this paper. This research was supported in part by ONR grants N00014-79C-0661 and N0014-82-C-50767. and DARPA contract number F33615-84K-1520. THE ACQUISITION OF PROCEDURAL KNOWLEDGE THROUGH INDUCTIVE LEARNING Kaihu Chen Artificial Intelligence Laboratory.

Two hypotheses HI and H2 describing the same class. if HI and H2 are equally efficacious 1 in describing the class. and HI is more general than H2. then H2 may be eliminated from further refinement. Similar refinement heuristics based on the relationship of two or more hypotheses can be defined. For example. associations between competing hypotheses can be established so that hypotheses with higher degree of association can be specialized to a common specialization to form a new hypothesis. Competing hypotheses with high degree of syntactical similarity can also be generalized to a common generalization.

Download PDF sample

Rated 4.11 of 5 – based on 12 votes