Steps toward Artificial Intelligence

@article{Minsky1961StepsTA,
  title={Steps toward Artificial Intelligence},
  author={M. Minsky},
  journal={Proceedings of the IRE},
  year={1961},
  volume={49},
  pages={8-30}
}
  • M. Minsky
  • Published 1961
  • Computer Science
  • Proceedings of the IRE
The problems of heuristic programming-of making computers solve really difficult problems-are divided into five main areas: Search, Pattern-Recognition, Learning, Planning, and Induction. [...] Key Result Wherever appropriate, the discussion is supported by extensive citation of the literature and by descriptions of a few of the most successful heuristic (problem-solving) programs constructed to date.Expand
A Framework for Searching for General Artificial Intelligence
TLDR
This document seeks to describe and unify principles that guide the basis of the development of general artificial intelligence, and defines intelligence as the ability to acquire skills that narrow this search, diversify it and help steer it to more promising areas. Expand
Heuristic Search Programs
TLDR
A heuristic is a rule of thumb, strategy, method or trick used to improve the efficiency of a system which tries to discover the solutions of complex problems to consider heuristic search techniques. Expand
Discovery and learning techniques for pattern recognition
TLDR
A program that makes a beginning attempt at using discovery and induction methods embedded within a pattern recognition program to provide powerful techniques for use in such research areas as form perception, target recognition, language translation, theorem proving, game playing, and the testing of psychological models is described. Expand
The heuristic of George Polya and its relation to artificial intelligence
Abstract : Polya's fundamental work in heuristic is well known and well regarded in artificial intelligence. However, no one has built seriously on his work, e. g., by constructing programs that makeExpand
Machine learning of heuristics
TLDR
This application, involving the construction of a computer program, demonstrates that few production rules or training trials are needed to produce a thorough and effective set of heuristics for draw poker. Expand
Artificial Intelligence: From programs to solvers
TLDR
The problem of generality in AI is revisited, the way in which this ’Models and Solvers’ agenda addresses the problem is looked at, and the relevance of this agenda to the grand AI goal of a computational account of intelligence and human cognition is discussed. Expand
Programs for Machine Learning. Part I
TLDR
A proposed schema and some detailed specifications for constructing a learning system by means of programming a computer are given, trying to separate learning processes and problem-solving techniques from specific problem content in order to achieve generality. Expand
Search in Artificial Intelligence
TLDR
This book brings together some new insights and recent developments on the topics of search procedures in Artificial Intelligence and the relationships among search methods in Artificial intelligence, Operations Research, and Engineering in a manner accessible to students and professionals in Computer Science, Engineering, Operations research, and Applied Mathematics. Expand
Generalization Learning Techniques for Automating the Learning of Heuristics
TLDR
Procedures are developed which permit a problem-solving program employing heuristics in production rule form to learn to improve its performance by evaluating and modifying existingHeuristics and hypothesizing new ones, either during an explicit training process or during normal program operation. Expand
Some recent work in artificial intelligence
TLDR
This paper will review certain approaches to artifical intelligence research--mainly work done since 1960, and some work in linguistics and pattern recognition is directly concerned with the induction problem. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 148 REFERENCES
Some Studies in Machine Learning Using the Game of Checkers
  • A. Samuel
  • Computer Science
  • IBM J. Res. Dev.
  • 1959
TLDR
The studies reported here have been concerned with the programming of a digital computer to behave in a way which would be described as involving the process of learning. Expand
Pattern recognition by machine
TLDR
Except for their inability to recognize patterns, machines have now met most of the classic criteria of intelligence that skeptics have proposed. Expand
Proving theorems by pattern recognition I
  • H. Wang
  • Mathematics, Computer Science
  • Commun. ACM
  • 1960
TLDR
It now appears that as more progress is made, strategies in the search for proofs, or what are often called heuristic methods, will also gradually become part of the subject matter of inferential analysis. Expand
A Learning Machine: Part I
TLDR
It is proposed that the program of a stored-program computer be gradually improved by a learning procedure which tries many programs and chooses, from the instructions that may occupy a given location, the one most often associated with a successful result. Expand
Intelligent Behavior in Problem-Solving Machines
TLDR
The concept of a theory machine as an extension of a theorem-proving machine is introduced and the authors consider the particular case of a machine that can prove theorems in elementary Euclidean plane geometry. Expand
Pattern Detection and Recognition
  • S. Unger
  • Computer Science
  • Proceedings of the IRE
  • 1959
TLDR
Two types of pattern-processing problems are discussed in this paper and recognition and detection have been successfully carried out on an IBM 704 computer programmed to simulate a spatial computer (a stored-program machine comprised of a master control unit directing a network of logical modules). Expand
Empirical explorations of the logic theory machine: a case study in heuristic
TLDR
The Logic Theory Machine is devised to learn how it is possible to solve difficult problems such as proving mathematical theorems, discovering scientific laws from data, playing chess, or understanding the meaning of English prose. Expand
The Inversion of Functions Defined by Turing Machines
TLDR
This paper deals with the problem of designing a Turing machine which, when confronted by the number pair, computes as efficiently as possible a function g(m, r) such that fm(g( m, r)) = r. Expand
On the Mechanical Simulation of Habit-Forming and Learning
  • S. Gorn
  • Computer Science
  • Inf. Control.
  • 1959
TLDR
This paper discusses digital techniques by which habit-forming and learning may be simulated, focusing attention upon reinforcement, and uses the language of computer programming to describe the flow of control and mathematical probability to analyze the effect of various reinforcement functions on the asymptotic behavior of simulating programs. Expand
A Learning Machine: Part II
An effort is made to improve the performance of the learning machine described in Part I, and the over-all effect of various changes is considered. Comparative runs by machines without the scoringExpand
...
1
2
3
4
5
...