On Tuesday, 28 June 2016 at 03:29:46 UTC, jmh530 wrote:
On Monday, 27 June 2016 at 22:17:55 UTC, Martin Nowak wrote:[...]I could probably write a simple backpropogation one, but I would probably screw something up if I wrote my own convolutional neural network.[...]
I am planning to provide OpenCL and CUDA targets to ldc in the next few weeks, probably starting in earnest next week, allowing direct compilation and calling code on the gpu automagically with reflection.
