Explaining ReLU as a Switch - another way
![]() |
In-going weights w in the ReLU neuron's layer. Out-going weights w' of the ReLU neuron (part of the next neural network layer's weights.) |
A (ReLU) neuron has in-going weight connections and out-going weight connections (some of the weights in the next layer.)
When the output of a ReLU neuron is zero those out-going weights are disconnected from the system. They don’t do anything.
When the output of the ReLU(x) function is active (x>0) then x=ReLU(x). It’s like the ReLU function wasn’t there (x=x). And the out-going weights of the neuron are directly connected to the sum of the in-going weights.
You dealing with a switched linear system.
Then you are freed up to think of other ways of switching in and out other blocks of weights.
Comments
Post a Comment