This guide will detail the limitations that sPyNNaker imposes on users of PyNN.
sPyNNaker implements a subset of the PyNN 0.7 API.
Model Type Limitations
sPyNNaker currently only supports the following model types:
- Leaky intergrate and fire current exponential IFCurrExp
- Leaky intergrate and fire conductive exponential IFCondExp
- Leaky intergrate and fire duel current exponential IFCurrDualExp
- Izhikevich Current Exponential Population IZKCurrExp
sPyNNaker currently supports these two models for injecting spikes into a PyNN model:
Currently, only the i_offset parameter of the neural models can be used to inject current.
sPyNNaker currently supports the following connector types:
- All to All connector AllToAllConnector
- Distance dependent probability connector DistanceDependentProbabilityConnector
- Fixed number pre connector FixedNumberPreConnector
- Fixed probability connector FixedProbabilityConnector
- From file connector FromFileConnector
- From list connector FromListConnector
- Multapse connector MultapseConnector
- One to one connector OneToOneConnector
sPyNNaker currently only supports plasticity described by an
STDPMechanism which is set as the
slow property of
sPyNNaker supports the following STDP timing dependence rules:
and the following STDP weight dependence rules:
- Additive weight dependence AdditiveWeightDependence
- Multiplicative weight dependence MultiplicativeWeightDependence
sPyNNaker also imposes the following limitations:
- All of our neural models have a limitation of 256 neurons per core. Depending on which SpiNNaker board you are using, this will limit the number of neurons that can be supported in any simulation.
- All our models support delays between 1 timestep and 144 timesteps. Delays of more than 16 timesteps are supported by delay extensions which take up another core within the machine, thus use of such delays will further limit the total number of neurons that can be supported in any simulation.