911 search results - page 122 / 183 » Combining programs and state machines |
NECO
2007
13 years 8 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...
SC
2009
ACM
14 years 3 months ago
2009
ACM
Recent and future parallel clusters and supercomputers use SMPs and multi-core processors as basic nodes, providing a huge amount of parallel resources. These systems often have h...
PPDP
1999
Springer
14 years 1 months ago
1999
Springer
For a compiler writer, generating good machine code for a variety of platforms is hard work. One might try to reuse a retargetable code generator, but code generators are complex a...
JMLR
2006
13 years 8 months ago
2006
While classical kernel-based learning algorithms are based on a single kernel, in practice it is often desirable to use multiple kernels. Lanckriet et al. (2004) considered conic ...
ICML
1989
IEEE
14 years 24 days ago
1989
IEEE
The training experiences needed by a learning system may be selected by either an external agent or the system itself. We show that knowledge of the current state of the learner&#...