- Padding added to sparse convolutional layers
- Sparse convolutional layers implemented in GPU backend (Kepler+ only)
- Fixed bug with dropout when error function is fuzed with last activation function
- Array with random numbers extended to 256K elements (for dropout)
Nov 30, 2014
nnForge v1.1.11
Hi, I am releasing nnForge v1.1.11 with a number of significant changes:
Nov 3, 2014
nnForge v1.1.10
Hi, here is nnForge v1.1.10. The main new feature is zero-padding for convolutional layers, I should have implemented it long before. The full list of changes:
- You can now specify zero-padding for input data for convolutional layers
- Memory usage calculations improved
- Learning rates is per part now (was per parameter) - training consumes less memory, bigger networks might be trained
- Dropout implementation is simplified
- Minor fixes
Subscribe to:
Posts (Atom)