Seanny123

from scipy.signal import lti

def synthetic_neuron(drive):
    """
    Simulates a mock neuron with a time step of 1ms.
    Arguments:
    drive - input to the neuron (expect zero mean; SD=1)
    Returns:
    rho - response function (0=non-spike and 1=spike at each time step)
    """

Seanny123

import pandas as pd
import numpy as np
from collections import OrderedDict
import re

import ipdb

terms = OrderedDict([
    ("loss", []),
    ("acc", []),

Seanny123

class AltEcho(Network, Reservoir):

    n_neurons = IntParam('n_neurons', default=None, low=1)
    dimensions = IntParam('dimensions', default=None, low=1)
    dt = NumberParam('dt', low=0, low_open=True)
    recurrent_synapse = SynapseParam('recurrent_synapse')
    gain = NumberParam('gain', low=0, low_open=True)
    neuron_type = NeuronTypeParam('neuron_type')

    def __init__(self, n_neurons, dimensions, recurrent_synapse=0.005,

Seanny123

import numpy as np
import nengo

model = nengo.Network()
tau = 0.1
ENS_SEED = 1
ENS_N_NEURONS = 100

with model:
  # map from an oscilator to a pattern

Seanny123

import nengo
import numpy as np

fsp_res = 4

with nengo.Network() as model:

    def in_func(t, x):
        idx = int((t * 100) % fsp_res)
        val = np.ones(fsp_res)

Seanny123

import numpy as np

arr = ["A", "B", "C", "D"]

# I want this to cycle every 0.5s
# so I should see this list printed twice
# with each item printed 5 times
idx = 0
arr_len = len(arr)
t_len = 0.5

Seanny123

8.542434789160060007e-04,-1.350971841367669402e-03,1.550384660972889406e-03,-1.307484519870601028e-03,2.107574646523068668e-04,3.237310053764653507e-03,1.394481474505514240e-01,-1.792572594477088305e-02,-2.111017965516969602e-02
3.533282465411854457e-04,-1.791492879237178287e-04,-1.855709995653045778e-05,-1.743758953232064799e-05,-5.210966224063090816e-04,8.930201575643531564e-03,1.484517136801228286e-02,-5.073399737080908599e-03,-4.473903762570220072e-03
3.489375633978934526e-04,2.451122643889763362e-04,-3.875986947442373572e-04,-1.169205067765441490e-04,-9.721645615909121994e-04,2.279935780598136771e-02,-3.499863181452933167e-03,-8.442464679787089685e-03,-5.066224544366498307e-03
3.980971182798381065e-04,5.015236582029211241e-04,-3.386030423717702469e-04,-1.515841152880205217e-04,-9.852177501969410639e-04,3.279147360274248940e-02,-5.284202821373784088e-03,-1.248557779964556969e-02,-7.195257440400722876e-03
5.126948644180514148e-04,1.014624534055026325e-03,-6.748874637068998008e-04,-3.067420521247723108e-04,

Seanny123

import nengo

# create a configuration for a threshold of 0.3
thresh_config = nengo.presets.ThresholdingEnsembles(0.3)

with nengo.Network() as model:
    # make a cycling ramp input to show the threshold is working
    in_node = nengo.Node(lambda t: 2*(t % 1) - 1)

    # make an ensemble with the thresholding configuration

Seanny123

import nengo
from nengo import spa

D = 32

vocab = spa.Vocabulary(D)

vocab.add("CALI", vocab.parse("0.1*WHITE + 0.9*HISPANIC"))
vocab.add("KANSAS", vocab.parse("0.7*WHITE + 0.3*HISPANIC"))

Seanny123

"""
Iterates through a directory of exported MindMup .mup files and prints the title of each file that matches the given
regular expression, as well as the matched node contents.

MindMup is a mind mapping tool which represents the Directed Acyclic Graph (DAG) of a mind map as a nested dictionary encoded as JSON.
"""

import argparse
import json
from pathlib import Path