A guide to the literature on learning probabilistic networks from data

W Buntine - IEEE Transactions on knowledge and data …, 1996 - ieeexplore.ieee.org
The literature review presented discusses different methods under the general rubric of
learning Bayesian networks from data, and includes some overlapping work on more …

Rule extraction from recurrent neural networks: Ataxonomy and review

H Jacobsson - Neural Computation, 2005 - direct.mit.edu
Rule extraction (RE) from recurrent neural networks (RNNs) refers to finding models of the
underlying RNN, typically in the form of finite state machines, that mimic the network to a …

[PDF][PDF] A guide to recurrent neural networks and backpropagation

M Boden - the Dallas project, 2002 - wiki.eecs.yorku.ca
This paper provides guidance to some of the concepts surrounding recurrent neural
networks. Contrary to feedforward networks, recurrent networks can be sensitive, and be …

[图书][B] A field guide to dynamical recurrent networks

JF Kolen, SC Kremer - 2001 - books.google.com
Acquire the tools for understanding new architectures and algorithms of dynamical recurrent
networks (DRNs) from this valuable field guide, which documents recent forays into artificial …

A recurrent neural network that learns to count

P Rodriguez, J Wiles, JL Elman - Connection Science, 1999 - Taylor & Francis
Parallel distributed processing (PDP) architectures demonstrate a potentially radical
alternative to the traditional theories of language processing that are based on serial …

Towards a generalized theory comprising digital, neuromorphic and unconventional computing

H Jaeger - Neuromorphic Computing and Engineering, 2021 - iopscience.iop.org
The accelerating race of digital computing technologies seems to be steering towards
impasses—technological, economical and environmental—a condition that has spurred …

Learning finite state representations of recurrent policy networks

A Koul, S Greydanus, A Fern - arXiv preprint arXiv:1811.12530, 2018 - arxiv.org
Recurrent neural networks (RNNs) are an effective representation of control policies for a
wide range of reinforcement and imitation learning problems. RNN policies, however, are …

Interest point detector and feature descriptor survey

S Krig, S Krig - Computer Vision Metrics: Textbook Edition, 2016 - Springer
Many algorithms for computer vision rely on locating interest points, or keypoints in each
image, and calculating a feature description from the pixel region surrounding the interest …

The dynamics of discrete-time computation, with application to recurrent neural networks and finite state machine extraction

M Casey - Neural computation, 1996 - direct.mit.edu
Recurrent neural networks (RNNs) can learn to perform finite state computations. It is shown
that an RNN performing a finite state computation must organize its state space to mimic the …

Markovian architectural bias of recurrent neural networks

P Tino, M Cernansky… - IEEE Transactions on …, 2004 - ieeexplore.ieee.org
In this paper, we elaborate upon the claim that clustering in the recurrent layer of recurrent
neural networks (RNNs) reflects meaningful information processing states even prior to …