Created
October 24, 2017 20:49
-
-
Save benjamingorman/a04387fbe3119801824aea2b6b53cab5 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import math | |
import numpy as np | |
import sys | |
lattice_width = 100 | |
lattice_height = 100 | |
initial_learning_rate = 0.01 | |
input_dimensions = 3 | |
weights = np.random.rand(lattice_height, lattice_width, input_dimensions) | |
initial_neighbourhood_radius = 15.0 | |
neighbourhood_shrink_factor = 1000.0 | |
def discriminant_function(w1, w2): | |
s = 0 | |
for i in range(len(w1)): | |
s += math.pow(w2[i] - w1[i], 2) | |
return s | |
def find_winning_neuron(pattern, weights): | |
best_d = sys.float_info.max | |
best_neuron = (0, 0) | |
for y in range(lattice_height): | |
for x in range(lattice_width): | |
neuron_weights = weights[y][x] | |
d = discriminant_function(neuron_weights, pattern) | |
print(d) | |
if d < best_d: | |
best_d = d | |
best_neuron = (x, y) | |
print("best d", best_d) | |
print("best neuron", best_neuron) | |
return best_neuron | |
def neighbourhood_size(time): | |
global initial_neighbourhood_radius, neighbourhood_shrink_factor | |
return initial_neighbourhood_radius * math.exp(-time / neighbourhood_shrink_factor) | |
def neighbourhood_function(neuron1, neuron2, time): | |
(x1, y1) = neuron1 | |
(x2, y2) = neuron2 | |
dist = math.pow(x2 - x1, 2) + math.pow(y2 - y1, 2) | |
T = math.exp(-dist / 2 * neighbourhood_size(time)) | |
return T |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment