Abstract | ||
---|---|---|
In this paper we present a novel algorithm, CarpeDiem. It significantly improves on the time complexity of Viterbi algorithm, preserving the optimality of the result. This fact has consequences on Machine Learning systems that use Viterbi algorithm during learning or classification. We show how the algorithm applies to the Supervised Sequential Learning task and, in particular, to the HMPerceptron algorithm. We illustrate CarpeDiem in full details, and provide experimental results that support the proposed approach. |
Year | DOI | Venue |
---|---|---|
2007 | 10.1145/1273496.1273529 | ICML |
Keywords | Field | DocType |
supervised sequential learning task,viterbi algorithm,novel algorithm,fast evaluation,full detail,machine learning system,time complexity,hmperceptron algorithm,ssl classifier,machine learning | Computer science,Wake-sleep algorithm,Artificial intelligence,Time complexity,Population-based incremental learning,Sequence learning,Viterbi algorithm,Weighted Majority Algorithm,Dynamic programming,Pattern recognition,Algorithm,Generalization error,Machine learning | Conference |
Citations | PageRank | References |
6 | 0.47 | 11 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Roberto Esposito | 1 | 64 | 10.87 |
Daniele P. Radicioni | 2 | 165 | 23.17 |