Sciweavers

2467 search results - page 372 / 494
» Finite State Machines
Sort
View
101
Voted
EAAI
2007
135views more  EAAI 2007»
15 years 21 days ago
Automatic generation of explanations: AGE
Explaining how engineering devices work is important to students, engineers, and operators. In general, machine generated explanations have been produced from a particular perspec...
Silvia B. González-Brambila, Eduardo F. Mor...
102
Voted
NECO
2007
115views more  NECO 2007»
15 years 7 days ago
Training Recurrent Networks by Evolino
In recent years, gradient-based LSTM recurrent neural networks (RNNs) solved many previously RNN-unlearnable tasks. Sometimes, however, gradient information is of little use for t...
Jürgen Schmidhuber, Daan Wierstra, Matteo Gag...
104
Voted
JAIR
2010
131views more  JAIR 2010»
14 years 11 months ago
Automatic Induction of Bellman-Error Features for Probabilistic Planning
Domain-specific features are important in representing problem structure throughout machine learning and decision-theoretic planning. In planning, once state features are provide...
Jia-Hong Wu, Robert Givan
SIGSOFT
2010
ACM
14 years 10 months ago
Realizability analysis for message-based interactions using shared-state projections
The global interaction behavior in message-based systems can be specified as a finite-state machine defining acceptable sequences of messages exchanged by a group of peers. Realiz...
Sylvain Hallé, Tevfik Bultan
156
Voted
GECCO
2011
Springer
240views Optimization» more  GECCO 2011»
14 years 4 months ago
Collisions are helpful for computing unique input-output sequences
Computing unique input-output sequences (UIOs) from finite state machines (FSMs) is important for conformance testing in software engineering, where evolutionary algorithms (EAs)...
Chao Qian, Yang Yu, Zhi-Hua Zhou