Published October 8, 2025 | Version ml_genn_2_4_0

genn-team/ml_genn: mlGeNN 2.40

  • 1. @ImperialCollegeLondon
  • 2. Imperial College London
  • 3. CBIT Open Source Community

Description

This release adds a number of new features to mlGeNN as well as including a number of bug fixes that have been identified since the 2.3.1 release. This version requires GeNN 5.1.0.

User Side Changes

  • Added 'Relative mean square' loss function inspired by DelGrad (#157)
  • Added Deep R rewiring support to EPropCompiler (#94)
  • Added warning for case when a model is compiled using EventPropCompiler without any readouts by (#151)

Bug fixes

  • Fixed issue where sparse cross-entropy loss function didn't work with batch size 1 (#154)

New Contributors

Massive thanks to our new contributor @s0hei1 who made their first contribution in #151

Files

genn-team/ml_genn-ml_genn_2_4_0.zip

Files (794.0 kB)

Name Size Download all
md5:94dda874da135a6975917e12ffb8c79a
794.0 kB Preview Download

Additional details

Related works

Software