Toward a Neural-Symbolic Sigma: Introducing Neural Network Learning (bibtex)

by Paul S. Rosenbloom, Abram Demski, Volkan Ustun

Abstract:

Building on earlier work extending Sigma’s mixed (symbols + probabilities) graphical band to inference in feedforward neural networks, two forms of neural network learning – target propagation and backpropagation – are introduced, bringing Sigma closer to a full neural-symbolic architecture. Adapting Sigma’s reinforcement learning (RL) capability to use neural networks in policy learning then yields a hybrid form of neural RL with probabilistic action modeling.

Reference:

Toward a Neural-Symbolic Sigma: Introducing Neural Network Learning (Paul S. Rosenbloom, Abram Demski, Volkan Ustun), In Proceedings of the 15th Annual Meeting of the International Conference on Cognitive Modelling, 2002–2017 EasyChair, 2017.

Bibtex Entry:

@inproceedings{rosenbloom_toward_2017, address = {Coventry, United Kingdom}, title = {Toward a {Neural}-{Symbolic} {Sigma}: {Introducing} {Neural} {Network} {Learning}}, url = {http://cs.usc.edu/~rosenblo/Pubs/ESNNL%20D.pdf}, abstract = {Building on earlier work extending Sigma’s mixed (symbols + probabilities) graphical band to inference in feedforward neural networks, two forms of neural network learning – target propagation and backpropagation – are introduced, bringing Sigma closer to a full neural-symbolic architecture. Adapting Sigma’s reinforcement learning (RL) capability to use neural networks in policy learning then yields a hybrid form of neural RL with probabilistic action modeling.}, booktitle = {Proceedings of the 15th {Annual} {Meeting} of the {International} {Conference} on {Cognitive} {Modelling}}, publisher = {2002–2017 EasyChair}, author = {Rosenbloom, Paul S. and Demski, Abram and Ustun, Volkan}, month = jul, year = {2017}, keywords = {Virtual Humans, UARC} }

Powered by bibtexbrowser