Here are my solutions to
Implementing Our Network to Classify Digits
Write out in component form, and verify that it gives the same result as the rule,
, for computing the output of a sigmoid neuron.
Let it be stated that I have not yet taken linear algebra at college, so I have very limited
experience with it.
Let us say that layer 2 has nodes and layer 1 has nodes.
The weights from layer 1 to layer 2 can be expressed as the following (, where is the
neuron in the second layer and is the neuron in the first layer):
This is exactly the same as but computed for both neurons
at once with matrices!
Say we wanted to compute the output of the first sigmoid neuron in layer 2.
Also, I wanted to note that I found this website called the
ml cheatsheet and it has been
really useful in describing the mathematic concepts.
The header image was taken from