Toy Neural Network Library in Go.
inputs -> [?] -> outputs
Out Range bounds = -1 -> 1
Supervised learning
What happens inside the neuron?
Missing pieces...(Weights and biases)
Perceptron creates a sum of all inputs multiplied by their weights.
Example: 2 in -> perceptron -> 2 out
sum(X(0) * W(0) + X(1) * W(1))
- Activation function (map to output range) (Sigmoid, sign, tanh, etc)
This is sometimes referred to as a "Feed Forward Neural Network"
Perceptron Algorithm
- For every input multiply that input by its weight.
- Sum all of the weighted inputs.
- Compute the output of the perceptron based on that sum passed through an activation function
Supervised Learning Algorithm
- Provide the perceptron with inputs for which there is a known answer.
- Ask the perceptron to guess an answer.
- Comput the error. (Did it get the answer right or wrong?)
- Adjust all the weights according to the error.
- GOTO 1
โW = Error / Input
New Weight = Weight + Error * Input * Learning Rate
Calculate using "Gradient Descent"