Skip to main content
Join the official Python Developers Survey 2018 and win valuable prizes: Start the survey!

Stuff made on the machine learning course at my university

Project description

Stuff made on the machine learning course at my university

Simple neuron

Instantiating a neuron with a sigmoid transfer function:

from am2 import Neuron, SigmoidTransferFunction

neuron = Neuron(SigmoidTransferFunction, weights=[0, 1, 1])
print neuron.run([3, 2, 1])

Or with a staircase transfer function:

from am2 import Neuron, StaircaseTransferFunction

neuron = Neuron(StaircaseTransferFunction, function=lambda y: y > 2, weights=[0, 1, 1])
print neuron.run([1, 1, 1])

function is optional (default is lambda y: y >= 1)

Perceptron

A simple Perceptron is implemented:

from am2 import Perceptron

train_dataset = [
    ((1, 0, 0), 1),
    ((1, 0, 1), 1),
    ((1, 1, 0), 1),
    ((1, 1, 1), 0),
]

perceptron = Perceptron(function=lambda y: y >= 1)
perceptron.train(train_dataset)  # executa o algoritmo de treinamento

print perceptron.run((1, 0, 0))

Project details


Release history Release notifications

This version
History Node

0.1

Supported by

Elastic Elastic Search Pingdom Pingdom Monitoring Google Google BigQuery Sentry Sentry Error logging AWS AWS Cloud computing DataDog DataDog Monitoring Fastly Fastly CDN SignalFx SignalFx Supporter DigiCert DigiCert EV certificate StatusPage StatusPage Status page