Issue No. 02 - April (1995 vol. 7)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/69.382304
<p><it>Abstract</it>—We propose a novel unified approach for integrating explicit knowledge and learning by example in recurrent networks. The explicit knowledge is represented by automaton rules, which are directly injected into the connections of a network. This can be accomplished by using a technique based on linear programming, instead of learning from random initial weights. Learning is conceived as a refinement process and is mainly responsible for uncertain information management. We present preliminary results for problems of automatic speech recognition.</p>
Recurrent neural networks, learning automata, automatic speech recognition.
G. Soda, M. Gori, M. Maggini and P. Frasconi, "Unified Integration of Explicit Knowledge and Learning by Example in Recurrent Networks," in IEEE Transactions on Knowledge & Data Engineering, vol. 7, no. , pp. 340-346, 1995.