som_colors.py

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