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
# Daniel J. Rodriguez | |
# https://github.com/danieljoserodriguez | |
import numpy as np | |
# A straight line function where activation is proportional to input | |
# ( which is the weighted sum from neuron ). | |
# In mathematics, an identity function, also called an identity relation or |
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
# Daniel J. Rodriguez | |
# https://github.com/danieljoserodriguez | |
# This Gist is for information purposes only to demonstrate how to perform the task at hand. | |
# I do not advise using this in a production environment - rather - for learning on your own | |
# multiple inputs and layers neural network | |
import numpy as np | |
# neuron layers |
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
# Daniel J. Rodriguez | |
# https://github.com/danieljoserodriguez | |
# This Gist is for information purposes only to demonstrate how to perform the task at hand. | |
# I do not advise using this in a production environment - rather - for learning on your own. | |
# simple multiple inputs neural network | |
######################################################################## | |
# just python - no extra libraries | |
def sum_weights(inputs, weights): |
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
# Daniel J. Rodriguez | |
# https://github.com/danieljoserodriguez | |
# This Gist is for information purposes only to demonstrate how to perform the task at hand. | |
# I do not advise using this in a production environment - rather - for learning on your own. | |
# simplest neural network - single input / neuron | |
neuron_weight = 0.1 | |
test_scores = [99, 75] | |
neuron_prediction = test_scores[0] * neuron_weight |
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
# Daniel J. Rodriguez | |
# https://github.com/danieljoserodriguez | |
import numpy as np | |
# Cross-entropy loss, or log loss, measures the performance of a classification model whose output is a | |
# probability value between 0 and 1 | |
def cross_entropy(y_hat, y): | |
return -np.log(y_hat) if y == 1 else -np.log(1 - y_hat) |