# Neural Networks

 Revision as of 05:29, 26 February 2011 (view source)Ang (Talk | contribs) (Created page with "Consider a supervised learning problem where we have access to labeled training examples $(x^{(i)}, y^{(i)})$. Neural networks give a way of defining a complex, non-l...")← Older edit Revision as of 05:36, 26 February 2011 (view source)Ang (Talk | contribs) Newer edit → Line 8: Line 8: diagram to denote a single neuron: diagram to denote a single neuron: - INSERTGRAPHICSHERE + [[Image:SingleNeuron.png|400px|center]] - This `neuron' is a computational unit that takes as input $x_1, x_2, x_3$ (and a +1 intercept term), and + This "neuron" is a computational unit that takes as input $x_1, x_2, x_3$ (and a +1 intercept term), and outputs $h_{W,b}(x) = f(W^Tx) = f(\sum_{i=1}^3 W_{i}x_i +b)$, where $f : \Re \mapsto \Re$ is outputs $h_{W,b}(x) = f(W^Tx) = f(\sum_{i=1}^3 W_{i}x_i +b)$, where $f : \Re \mapsto \Re$ is called the '''activation function'''.  In these notes, we will choose called the '''activation function'''.  In these notes, we will choose