notes

Personal notes
git clone git://git.laack.co/notes.git
Log | Files | Refs

WideAndDeepNN.md (567B)


      1 # Wide and Deep Neural Network
      2 
      3 ML D6
      4 
      5 **Definition:** Wide and deep neural networks are a model architecture where some or all inputs are connected directly to outputs while also having a path through the neural network through hidden layers.
      6 
      7 By using a wide and deep neural network we don't worry about muddying simple relationships through the long path of a neural network as some values will be automatically factored into the outputs. 
      8 
      9 When doing this you use a concatenation layer prior to the output layer to combine both the long and short paths together.