Connectionist expert systems

By Stephen I. Gallant. 1988

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Deep learning in neural networks: An overview (2014, neutral): “…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,…”
On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models (2015, methodology): “As the history grows, to find an M with small bitsM + bitsH , step 4 uses sequential network construction: it regularly changes M ’s size by adding or pruning units and connections [111, 112, 8, 168, 59, 107, 304, 176, 141, 92, 143, 204, 53, 296, 106, 31, 57, 185, 283].”
Opening the black box - data driven visualization of neural networks (2005, methodology): “Rule extraction was (cid:2)rst mentioned by Gallant [11] to describe the neural networks with a more understandable representation.”
Artificial neural networks and their business applications (1994, background): “Gallant [6] demonstrated that an explanation ability can be incorporated into an ANN.”
State-of-the-art in artificial neural network applications: A survey (2018, methodology): “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].”
Natural Language Processing and Machine Learning (2016, unknown): “An explanation capability can also provide a check on the internal logic of the system as well as being able to give a novice insight into the problem [6].”
Neural, symbolic and neural-symbolic reasoning on knowledge graphs (2021, background): “The problem of combining symbolism and connectionism has been researched since the 1980s (Gallant, 1988, 1993; Shavlik et al., 1991; Towell and Shavlik, 1994a, 1994b), and has drawn much attention recent years (Besold et al., 2017; de Penning et al., 2011; Garcez et al., 2012, 2019; Lamb et al.,…”
Rule extraction from trained adaptive neural networks using artificial immune systems (2009, methodology): “The first rule extraction techniques from neural networks was proposed by Gallant (1988).”
FERNN: An Algorithm for Fast Extraction of Rules from Neural Networks (2004, background): “It is not surprising that in recent years there has been a signi cant amount of work devoted to the development of algorithms that extract rules from neural networks [1, 4, 7, 8, 18, 19, 21, 23].”
Extracting rules from multilayer perceptrons in classification problems: A clustering-based approach (2006, background): “In a later work, Gallant [20] developed the concepts relating NN learning with expert systems.”
Combining Symbolic and Neural Learning (1994, background): “ Gallant (1988) , Saito and Nakano (1988), and Fu (1991) proposed algorithms that consider various ways that a node's weighted input can exceed its threshold, and convert each of these situations into a rule.”
From LSAT: The Progress and Challenges of Complex Reasoning (2021, background): “c) Neural-Symbolic Models: To combine the advantages and circumvent the shortcomings of both symbolic and neural methods, neural-symbolic models which integrate symbolic logic and neural representation are widely studied [69, 70, 71, 72, 73].”