Lab 0: Virtual Environment Setup

Lab 0: Virtual Environment Setup#

Here, you will test your Virtual Environment.

Code cred

Set up#

Ensure you are using your 495 Virtual Environment before you begin!

Import Nengo and other supporting libraries into your program to get started:

import matplotlib.pyplot as plt
import numpy as np
import nengo
from nengo.dists import Uniform

from urllib.request import urlretrieve
import tensorflow as tf
import nengo_dl

This is code that you will understand in due time, get excited.#

This code is testing that we are set up to program Nengo neurons to represent values over time.

## Create Neuron
model = nengo.Network(label="A Single Neuron")
with model:
    neuron = nengo.Ensemble(
        1,
        dimensions=1,  # Represent a scalar
        # Set intercept to 0.5
        intercepts=Uniform(-0.5, -0.5),
        # Set the maximum firing rate of the neuron to 100hz
        max_rates=Uniform(100, 100),
        # Set the neuron's firing rate to increase for positive input
        encoders=[[1]],
    )

## Create Input
with model:
    cos = nengo.Node(lambda t: np.cos(8 * t))

## Connect Input to Neuron
with model:
    # Connect the input signal to the neuron
    nengo.Connection(cos, neuron)

## Add probes to view neuron response
with model:
    # The original input
    cos_probe = nengo.Probe(cos)
    # The raw spikes from the neuron
    spikes = nengo.Probe(neuron.neurons)
    # Subthreshold soma voltage of the neuron
    voltage = nengo.Probe(neuron.neurons, "voltage")
    # Spikes filtered by a 10ms post-synaptic filter
    filtered = nengo.Probe(neuron, synapse=0.01)

## Run model
with nengo.Simulator(model) as sim:  # Create the simulator
    sim.run(1)  # Run it for 1 second

This is where you should edit your code and print your results!#

## Plot the results!
# Plot the decoded output of the ensemble
plt.figure()
plt.plot(sim.trange(), sim.data[filtered])
plt.plot(sim.trange(), sim.data[cos_probe])
plt.xlim(0, 1)
plt.title( "Decoded Neuron Output - LastName" )
plt.show()

More code that you will understand in due time!#

This code is testing that we are set up to perform deep learning with Nengo neurons.

mnist = tf.keras.datasets.mnist

(train_images, train_labels), (test_images, test_labels) = mnist.load_data()

with nengo.Network(seed=0) as net:

    # NengoDL default parameters for the neurons that will make
    # the training progress more smoothly
    net.config[nengo.Ensemble].max_rates = nengo.dists.Choice([100])
    net.config[nengo.Ensemble].intercepts = nengo.dists.Choice([0])
    net.config[nengo.Connection].synapse = None
    neuron_type = nengo.LIF(amplitude=0.01)
    nengo_dl.configure_settings(stateful=False)

minibatch_size = 256
sim = nengo_dl.Simulator(net, minibatch_size=minibatch_size)
Contents