Hello folks,

I am trying to learn the weights for connections between the neurons of 2 ensembles (connected in all to all fashion). I used a transform matrix initialized with zeros, but it is not learning any weights. This is my code (I have used only one training sample for now):

```
with nengo.Network() as model:
x_inp = nengo.Node([1, 0, 0, 0, 1])
x = nengo.Ensemble(5, 1, intercepts=Choice([0.1]), max_rates=Choice([100]), neuron_type=nengo.LIF())
nengo.Connection(x_inp, x.neurons)
y_inp = nengo.Node([0, 1, 0, 1, 0])
y = nengo.Ensemble(5, 1, intercepts=Choice([0.1]), max_rates=Choice([100]), neuron_type=nengo.LIF())
nengo.Connection(y_inp, y.neurons)
conn = nengo.Connection(x.neurons, y.neurons, transform=weights, learning_rule_type=nengo.learning_rules.BCM()
```

However my initial weights still remains an all zero matrix (i.e. they do not get updated), and the connection weights are also all zeros. How can I correct this?