Commit 1ed123e3 authored by Erik Strand's avatar Erik Strand

Link to backprop notes from pset

parent a5f0e860
......@@ -139,3 +139,14 @@ $$
Here are the different errors.
![errors](../../assets/img/10_errors.png)
## 3
{:.question}
Train a neural network on the output from an order 4 maximal LFSR and learn to reproduce it. How do
the results depend on the network depth and architecture?
I have previously implemented backpropagation from scratch, to train my own
[VAEs](https://gitlab.cba.mit.edu/erik/gears/-/tree/master/gears/custom_networks). So rather than
write this again, I wrote up a better [derivation of backpropagation](../notes/backpropagation.html)
which I can use a reference for future modifications.
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment