September 18, 2015

DON'T PANIC

Helpful resources

Perceptron

Frank Rosenblatt & Mark 1 Perceptron

Single layer perceptron

Take input \(x_{p\times 1}\) and calculate the weighed input \(w\cdot x + b\), where

  • \(w_{p\times 1}\) is a vector of weights applied to the input, and
  • \(b\) is a scalar bias term that offsets the weighted sum

Now, classify x according to

\[output = \begin{cases} 0 & \text{if } w\cdot x + b \leq 0 \\ 1 & \text{if } w\cdot x + b > 0 \end{cases}\]

Binary classification

Binary classification

Binary classification

Binary classification