Nov 30, 2014

nnForge v1.1.11

Hi, I am releasing nnForge v1.1.11 with a number of significant changes:

  • 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 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