Nikhil Garg

Implementation of RNNs

1

I think the current framework does not support vanilla RNNs, LSTMs, GRUs. These are really useful in time-series signal processing. Is it possible to add conversion modules for the above...

The small world topology does not work

1

NotImplementedError Traceback (most recent call last) in () 58 receptor_type='excitatory', 59 synapse_type=sim.StaticSynapse(**synaptic_parameters['excitatory_simple']), ---> 60 label='Excitatory - Excitatory connections') 61 62 exc_inh_connections = sim.Projection(exc_cells, inh_cells, /Users/Anonymous/opt/anaconda2/lib/python2.7/site-packages/pyNN/brian/projections.pyc in __init__(self, presynaptic_population, postsynaptic_population, connector,...

In Brian backend, implemented STDP with Addative weight dependence and w_min = 0.1 But the final weight are negative

Declaration of array

1

I cannot declare array which works otherwise fine with Cadence: real PoffVector[1:500], Poff;