Connectionist expert systems
TL;DR: Connectionist networks can be used as expert system knowledge bases and can be constructed from training examples by machine learning techniques, giving a way to automate the generation of expert systems for classification problems.
Abstract: Connectionist networks can be used as expert system knowledge bases. Furthermore, such networks can be constructed from training examples by machine learning techniques. This gives a way to automate the generation of expert systems for classification problems.
Citations
More filters
TL;DR: This historical survey compactly summarizes relevant work, much of it from the previous millennium, review deep supervised learning, unsupervised learning, reinforcement learning & evolutionary computation, and indirect search for short programs encoding deep and large networks.
14,635 citations
Additional excerpts
...…and pruning algorithms, e.g., layer-by-layer sequential network construction (e.g., Ash, 1989; Burgess, 1994; Fahlman, 1991; Fritzke, 1994; Gallant, 1988; Honavar & Uhr, 1988, 1993; Ivakhnenko, 1968, 1971; Moody, 1989; Parekh, Yang, & Honavar, 2000; Ring, 1991; Utgoff & Stracuzzi,…...
[...]
..., layer-by-layer sequential network construction (e.g., Ash, 1989; Burgess, 1994; Fahlman, 1991; Fritzke, 1994; Gallant, 1988; Honavar & Uhr, 1988, 1993; Ivakhnenko, 1968, 1971; Moody, 1989; Parekh, Yang, & Honavar, 2000; Ring, 1991; Utgoff & Stracuzzi, 2002;Weng, Ahuja, & Huang, 1992) (see also Sections 5....
[...]
TL;DR: A general neural-network (connectionist) model for fuzzy logic control and decision systems is proposed, in the form of feedforward multilayer net, which avoids the rule-matching time of the inference engine in the traditional fuzzy logic system.
Abstract: A general neural-network (connectionist) model for fuzzy logic control and decision systems is proposed. This connectionist model, in the form of feedforward multilayer net, combines the idea of fuzzy logic controller and neural-network structure and learning abilities into an integrated neural-network-based fuzzy logic control and decision system. A fuzzy logic control decision network is constructed automatically by learning the training examples itself. By combining both unsupervised (self-organized) and supervised learning schemes, the learning speed converges much faster than the original backpropagation learning algorithm. The connectionist structure avoids the rule-matching time of the inference engine in the traditional fuzzy logic system. Two examples are presented to illustrate the performance and applicability of the proposed model. >
1,476 citations
Cites background from "Connectionist expert systems"
...Links at layers three and four function as a connectionist inference engine [29], [ 30 ], which avoids the rule-matching process....
[...]
TL;DR: The study found that neural-network models such as feedforward and feedback propagation artificial neural networks are performing better in its application to human problems and proposed feedforwardand feedback propagation ANN models for research focus based on data analysis factors like accuracy, processing speed, latency, fault tolerance, volume, scalability, convergence, and performance.
1,471 citations
Cites methods from "Connectionist expert systems"
...ANNs has many names as found in the literature such as; connectionism/connectivist models, adaptive systems, parallel distributed processing models, self-organizing systems, neuromorphic and neurocomputing systems [201, 202, 203, 204]....
[...]
TL;DR: After a decade of fundamental interdisciplinary research in machine learning, the spadework in this field has been done; the 1990s should see the widespread exploitation of knowledge discovery as an aid to assembling knowledge bases.
Abstract: After a decade of fundamental interdisciplinary research in machine learning, the spadework in this field has been done; the 1990s should see the widespread exploitation of knowledge discovery as an aid to assembling knowledge bases. The contributors to the AAAI Press book Knowledge Discovery in Databases were excited at the potential benefits of this research. The editors hope that some of this excitement will communicate itself to "AI Magazine readers of this article.
1,332 citations
Cites background from "Connectionist expert systems"
...A neural network, for example, might have to generate explanations from its weights (Gallant 1988)....
[...]
...A neural network, for example, might have to generate explanations from its weights (Gallant 1988)....
[...]
01 Jan 1991
TL;DR: In the 1990s, the AAAI Press book Knowledge Discovery in Databases was published, and the potential benefits of this research were discussed by the contributors to the book as discussed by the authors, who hope that some of this excitement will communicate itself to "AI Magazine readers of this article".
Abstract: After a decade of fundamental interdisciplinary research in machine learning, the spadework in this field has been done; the 1990s should see the widespread exploitation of knowledge discovery as an aid to assembling knowledge bases. The contributors to the AAAI Press book Knowledge Discovery in Databases were excited at the potential benefits of this research. The editors hope that some of this excitement will communicate itself to "AI Magazine readers of this article.
1,292 citations
References
More filters
TL;DR: A model of a system having a large number of simple equivalent components, based on aspects of neurobiology but readily adapted to integrated circuits, produces a content-addressable memory which correctly yields an entire memory from any subpart of sufficient size.
Abstract: Computational properties of use of biological organisms or to the construction of computers can emerge as collective properties of systems having a large number of simple equivalent components (or neurons). The physical meaning of content-addressable memory is described by an appropriate phase space flow of the state of a system. A model of such a system is given, based on aspects of neurobiology but readily adapted to integrated circuits. The collective properties of this model produce a content-addressable memory which correctly yields an entire memory from any subpart of sufficient size. The algorithm for the time evolution of the state of the system is based on asynchronous parallel processing. Additional emergent collective properties include some capacity for generalization, familiarity recognition, categorization, error correction, and time sequence retention. The collective properties are only weakly sensitive to details of the modeling or the failure of individual devices.
16,652 citations
17 Jul 1986
15,313 citations
TL;DR: In this article, it is shown that many particular choices among possible neurophysiological assumptions are equivalent, in the sense that for every net behaving under one assumption, there exists another net which behaves under another and gives the same results, although perhaps not in the same time.
14,937 citations
14,009 citations
01 Jan 1988
TL;DR: It is shown that many particular choices among possible neurophysiological assumptions are equivalent, in the sense that for every net behaving under one assumption, there exists another net which behaves under the other and gives the same results, although perhaps not in the same time.
Abstract: Because of the “all-or-none” character of nervous activity, neural events and the relations among them can be treated by means of propositional logic. It is found that the behavior of every net can be described in these terms, with the addition of more complicated logical means for nets containing circles; and that for any logical expression satisfying certain conditions, one can find a net behaving in the fashion it describes. It is shown that many particular choices among possible neurophysiological assumptions are equivalent, in the sense that for every net behaving under one assumption, there exists another net which behaves under the other and gives the same results, although perhaps not in the same time. Various applications of the calculus are discussed.
4,109 citations