Commit message (Collapse) | Author | Age | ||
---|---|---|---|---|
... | ||||
* | Added support for argmax/argmin | 2015-08-31 | ||
| | ||||
* | Use numext::mini/numext::maxi instead of std::min/std::max in the tensor code | 2015-08-28 | ||
| | ||||
* | Many files were missing in previous changeset. | 2015-07-29 | ||
| | ||||
* | Added support for sigmoid function to the tensor module | 2015-07-17 | ||
| | ||||
* | Added support for generation of random complex numbers on CUDA devices | 2015-07-07 | ||
| | ||||
* | Added a test for multithreaded full reductions | 2015-06-30 | ||
| | ||||
* | Added missing include files | 2015-05-28 | ||
| | ||||
* | Silenced a few compilation warnings | 2015-04-22 | ||
| | ||||
* | Added the ability to generate a tensor from a custom user defined ↵ | 2015-04-22 | ||
| | | | | | | 'generator'. This simplifies the creation of constant tensors initialized using specific regular patterns. Created a gaussian window generator as a first use case. | |||
* | Added support for non-deterministic random number generation on GPU | 2015-04-22 | ||
| | ||||
* | Silenced a few compilation warnings | 2015-04-20 | ||
| | ||||
* | Improved the tensor random number generators: | 2015-04-20 | ||
| | | | | | * Use a mersenne twister whenebver possible instead of the default entropy source since the default one isn't very good at all. * Added the ability to seed the generators with a time based seed to make them non-deterministic. | |||
* | Fixed a bug in the handling of packets by the MeanReducer | 2015-03-19 | ||
| | ||||
* | Added more tests to cover tensor reductions | 2015-01-28 | ||
| | ||||
* | Improved the performance of tensor reductions | 2015-01-14 | ||
| | | | | | Added the ability to generate random numbers following a normal distribution Created a test to validate the ability to generate random numbers. | |||
* | Improved the functors defined for standard reductions | 2014-10-09 | ||
| | | | | Added a functor to encapsulate the generation of random numbers on cpu and gpu. | |||
* | Added support for tensor reductions and concatenations | 2014-10-01 | ||