The weights are simply the coefficients that define a separating plane. For the moment, forget about neurons and just consider the geometric definition of a plane in N dimensions: w1*x1 + w2*x2 + … + wN*xN – w0 = 0 You can also think of this as being a dot product: w*x – w0 = … Read more
In your current code, the perceptron successfully learns the direction of the decision boundary BUT is unable to translate it. y y ^ ^ | – + \\ + | – \\ + + | – +\\ + + | – \\ + + + | – – \\ + | – – \\ + … Read more
how many hidden layers? a model with zero hidden layers will resolve linearly separable data. So unless you already know your data isn’t linearly separable, it doesn’t hurt to verify this–why use a more complex model than the task requires? If it is linearly separable then a simpler technique will work, but a Perceptron will … Read more