TY - GEN
T1 - A novel learning method by structural reduction of DAGs for on-line OCR applications
AU - Lin, I. Jong
AU - Kung, S. Y.
PY - 1998
Y1 - 1998
N2 - This paper introduces a learning algorithm for a neural structure, directed acyclic graphs (DAGs) that is structurally based, i.e. reduction and manipulation of internal structure are directly linked to learning. This paper extends the concepts of I-Jong Lin and Kung (see IEEE Transactions in Signal Processing Special Issue Neural Networks, 1996) for template matching to a neural structure with capabilities for generalization. DAG-learning is derived from concepts in finite state transducers, hidden Markov models, and dynamic time warping to form an algorithmic framework within which many adaptive signal techniques such as vector quantization, K-means, approximation networks, etc., may be extended to temporal recognition. The paper provides a concept of path-based learning to allow comparison among hidden Markov models (HMMs), finite state transducers (FSTs) and DAG-learning. The paper also outlines the DAG-learning process and provides results from the DAG-learning algorithm over a test set of isolated cursive handwriting characters.
AB - This paper introduces a learning algorithm for a neural structure, directed acyclic graphs (DAGs) that is structurally based, i.e. reduction and manipulation of internal structure are directly linked to learning. This paper extends the concepts of I-Jong Lin and Kung (see IEEE Transactions in Signal Processing Special Issue Neural Networks, 1996) for template matching to a neural structure with capabilities for generalization. DAG-learning is derived from concepts in finite state transducers, hidden Markov models, and dynamic time warping to form an algorithmic framework within which many adaptive signal techniques such as vector quantization, K-means, approximation networks, etc., may be extended to temporal recognition. The paper provides a concept of path-based learning to allow comparison among hidden Markov models (HMMs), finite state transducers (FSTs) and DAG-learning. The paper also outlines the DAG-learning process and provides results from the DAG-learning algorithm over a test set of isolated cursive handwriting characters.
UR - http://www.scopus.com/inward/record.url?scp=84892185652&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84892185652&partnerID=8YFLogxK
U2 - 10.1109/ICASSP.1998.675453
DO - 10.1109/ICASSP.1998.675453
M3 - Conference contribution
AN - SCOPUS:84892185652
SN - 0780344286
SN - 9780780344280
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 1069
EP - 1072
BT - Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 1998
T2 - 1998 23rd IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 1998
Y2 - 12 May 1998 through 15 May 1998
ER -