Document / parameterize hidden synapse from ensemble -> output

[arvoelke]

nengo-fpga/nengo_fpga/networks/fpga_pes_ensemble_network.py

Lines 185 to 188 in a19a29a

	self.connection = nengo.Connection(
	self.ensemble, self.output, function=function,
	transform=transform, eval_points=eval_points,
	learning_rule_type=nengo.PES(learning_rate))

A synapse (that is not directly configurable) is created on this connection to the output node. This results in slightly different results between FpgaPesEnsembleNetwork and a corresponding Ensemble both with the same nengo.Simulator. A workaround is to configure fpga_pes_ensemble_network.connection.synapse = None after creating the network.

Here's a quick unit test that demonstrates identical behaviour with this work-around:

import nengo
from nengo_fpga.networks import FpgaPesEnsembleNetwork

n = 1
neuron_type = nengo.SpikingRectifiedLinear()
rate = 100
probe_tau = 0.1
sim_t = 20

# 1) Nengo Ensemble implementation
with nengo.Network() as model1:
    a1 = nengo.Ensemble(
        n_neurons=n,
        dimensions=1,
        neuron_type=neuron_type,
        gain=np.zeros(n),
        bias=rate*np.ones(n),
    )
    
    p1 = nengo.Probe(a1.neurons, synapse=probe_tau)
    
# 2) Equivalent FpgaPesEnsembleNetwork implementation
with nengo.Network() as model2:
    a2 = FpgaPesEnsembleNetwork(
        fpga_name='foobar',
        n_neurons=n,
        dimensions=n,
        learning_rate=0,
    )
    a2.ensemble.gain = np.zeros(n)
    a2.ensemble.bias = rate*np.ones(n)
    a2.ensemble.neuron_type = neuron_type
    a2.connection.solver = nengo.solvers.NoSolver(np.eye(n))
    a2.connection.synapse = None  # <- this is the important line
    
    p2 = nengo.Probe(a2.output, synapse=probe_tau)

# Compare for equality using the same simulator
with nengo.Simulator(model1) as sim1:
    sim1.run_steps(sim_t)

with nengo.Simulator(model2) as sim2:
    sim2.run_steps(sim_t)
    
assert np.allclose(sim1.data[p1], sim2.data[p2])

[arvoelke]

Found some unexpected behaviour with the above example. If I switch the second simulator to nengo_fpga.Simulator, the fpga_name to an existing board, and a2.connection.synapse to something other than None, then that synapse appears to be ignored. For instance, moving the probe_tau from the probe to the connection does not seem to work (the output is still spikes).