Week of June 7th
What I did
Recent Posts
PyTorch, A Quick Intro
Pytorch uses tensors instead, similar to a numpy array
Week of May 30th
What I did
Taylor Expansion of the RMS Prop Update Algorithm
RMSprop is similar to gradient descent with momentum, but takes into consideration the sign of the gradient like this:
The Dance of Forward Pass and Backprop
In order to implement a neural network, a solid understanding of Linear Algebra is needed for the forward pass, whereas vector calculus is needed for backpro...