TY - GEN
T1 - Inferring probabilistic acyclic automata using the minimum description length principle
AU - Singer, Yoram
AU - Tishby, Naftali
PY - 1994/12/1
Y1 - 1994/12/1
N2 - The use of Rissanen's (1978) minimum description length principle for the construction of probabilistic acyclic automata (PAA) is explored. We propose a learning algorithm for a PAA that is adaptive both in the structure and the dimension of the model. The proposed algorithm was tested on synthetic data as well as on real pattern recognition problems.
AB - The use of Rissanen's (1978) minimum description length principle for the construction of probabilistic acyclic automata (PAA) is explored. We propose a learning algorithm for a PAA that is adaptive both in the structure and the dimension of the model. The proposed algorithm was tested on synthetic data as well as on real pattern recognition problems.
UR - http://www.scopus.com/inward/record.url?scp=84894386259&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84894386259&partnerID=8YFLogxK
U2 - 10.1109/ISIT.1994.394627
DO - 10.1109/ISIT.1994.394627
M3 - Conference contribution
AN - SCOPUS:84894386259
SN - 0780320158
SN - 9780780320154
T3 - IEEE International Symposium on Information Theory - Proceedings
BT - Proceedings - 1994 IEEE International Symposium on Information Theory, ISIT 1994
T2 - 1994 IEEE International Symposium on Information Theory, ISIT 1994
Y2 - 27 June 1994 through 1 July 1994
ER -