[Nengo-DL]: Adding a dynamic custom layer between two Ensembles

[xchoo]

@zerone

I suppose you are talking about the convolution operation (between the synapse and the weighted spikes) implemented as Linear Transforms, and hence the order doesn’t matter.

Yes. That is correct. The synaptic application is a convolution operation and it doesn’t matter if you apply the convolution first, or do the connection weight matrix multiplication first.

@zerone

I suppose you are hinting towards the mathematical functions whose Decoders can be calculated, thus incorporated in the connection weight matrix along with transform. Right?

Correct!

@zerone

Let’s say a Convolutional transform has to be applied, then whatever is the output of the neurons of the previous Ensemble, NengoDL first applies the transform, and then applies the synapse on the resulted values. Is it?

Yes

@zerone

My doubt stands pretty much resolved, however, I would like to get some more clarifications. I see that the raw output is 10 (4), when scale_firing_rates is 100, (250) respectively, which is (amplitude/dt) / scale_firing_rate (assuming amplitude is 1 and dt is 0.001).

Yes. This is expected behaviour. Remember that the purpose of the scale_firing_rates parameter is to increase the firing rates of the neurons in the network. However, in order to keep the overall “energy” (or information) being transmitted by the network the same in both cases, the amplitudes of the spikes are divided by the scale_firing_rates value. From my other post:

@xchoo

To compensate for the increased firing rate, we divide the amplitude of the output spike by scale_firing_rates to keep the neuron’s total “energy” the same. Since a spike has a default amplitude of 1/dt, the new spike amplitude would be 1/(10*dt) = 1

@zerone

Is this the “input” to further computations in the connections, i.e. is function, or transform or synapse applied on (amplitude/dt) / scale_firing_rate (e.g. 10.0) in the nengo.Connection()? or are the above computations applied to the value of “spike amplitudes”

The scale_firing_rate parameter is applied directly to the amplitude of the neuron’s spikes. Similarly (on the input side), the scale_firing_rate parameter is applied directly to the neuron’s gains.

@zerone

For some reason, I am messing things up. Please clarify?

Just to clarify your earlier question. I believe you are conflating two different concepts here. Your original thought was that the scale_firing_rates would affect the amplitude by scaling it up. However, the purpose of the scale_firing_rates parameter is to increase (typically) the firing rates of the neurons (by adjusting the neuron gains). The reason the amplitude of the spikes is affected is because we want to keep the overall amount of information being transmitted by the spikes the same (pre and post-scaling). Since we scaled up the firing rate, the thing to do would be to scale down the amplitude, which in effect “cancels” out any additional information gain obtained by increasing the neuron gain.