v1.0.1
Sinabs is now stable!
- Addition of leaky models such as Leaky Integrate and Fire (LIF), Exponential Leaky (ExpLeak) and Adaptive LIF (ALIF).
- Activation module: from sinabs.activation you'll now be able to pick and choose different spike generation, reset mechanism and surrogate gradient functions. You can pass them to the neuron model (LIF, IAF, ...) of your liking if you want to alter the default behavior.
- new documentation on readthedocs and continuous integration pipeline on Github
- New neuron features: support for recurrent connections, recording internal states, normalising inputs by taus, initialisation with shape and more.