21 search results - page 4 / 5 » Programming backgammon using self-teaching neural nets |
VLSISP
1998
13 years 7 months ago
1998
Understanding of the scene content of a video sequence is very important for content-based indexing and retrieval of multimedia databases. Research in this area in the past severa...
EH
1999
IEEE
1999
IEEE
Evolvable Hardware or Learning Hardware? Induction of State Machines from Temporal Logic Constraints
13 years 11 months ago
Here we advocate an approach to learning hardware based on induction of finite state machines from temporal logic constraints. The method involves training on examples, constraint...
NIPS
1996
13 years 8 months ago
1996
Dynamic Programming, Q-learning and other discrete Markov Decision Process solvers can be applied to continuous d-dimensional state-spaces by quantizing the state space into an arr...
NECO
2007
13 years 6 months ago
2007
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...
ECAL
1995
Springer
13 years 11 months ago
1995
Springer
After an outline of the history of evolutionary algorithms, a new ( ) variant of the evolution strategies is introduced formally. Though not comprising all degrees of freedom, it i...