Skip to content

@tbekolay tbekolay released this Feb 22, 2019 · 4 commits to master since this release

Changed

  • New Nengo transforms are supported, including nengo.Convolution. Many of the classes previously in conv.py have been moved to Nengo as part of this transition. The MNIST convnet example demonstrates the new syntax. (#142)
  • Emulator now fails for any cx_base < 0, except -1 which indicates an unused axon. (#185)
  • Noise now works correctly with small exponents on both the chip and emulator. Previously, the emulator did not allow very small exponents, and such exponents produced noise with the wrong magnitude on the chip. (#185)
  • Models trained using NengoDL use tuning curves more similar to those of neuron on the chip, improving the accuracy of these model. (#140)

Removed

  • Removed the NIF and NIFRate neuron types. These types were only used for encoding node values in spikes to send to the chip, which can be done just as well with nengo.SpikingRectifiedLinear neurons. (#185)
  • Removed the unused/untested Synapse.set_diagonal_weights. (#185)

Fixed

  • Objects in nengo-loihi will have the same random seeds as in nengo core (and therefore any randomly generated parameters, such as ensemble encoders, will be generated in the same way). (#70)
  • Seeded networks that have learning are now deterministic on both emulator and hardware. (#140)
Assets 2
You can’t perform that action at this time.