Nevermind XOR
AI
deep learning experiment
SHOW HN2022
34points
10comments
#1,190of 2,570 in 2022
Top 47%of 2022 by points
How HN took it
QuietFewer than 5 comments about the project
0 positive, 1 neutral or asking, 0 mixed, 3 critical, out of 4 comments about the project.
Idea: 0 for, 2 againstDocs: 0 for, 1 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
Objections
Pointwise loss treats timepoints as independent; an autoregressive model would fit better.
From 1 comment
You're using a pointwise loss, which means you are treating each timepoint as conditionally independent. That's a deeply flawed assumption, probabilistically. Try an…
rryan on HN
A sin-based forward pass does not qualify as deep learning.
From 1 comment
> def forward(self, x): return torch.sin(self.freq * x) I don't think this qualifies as deep learning anyway
shreyshnaccount on HN
The problem is framed in a flawed way.
From 1 comment
yeah, and the way the problem is being treated is flawed, but that's another thing
shreyshnaccount on HN
Questions
How the maker concluded the x + sin(x) activation only worked when cycles were fewer than parameters.
From 1 comment
>Their x + sin(x) * 2 activation only really worked when the number of full cycles in the dataset was less than the number of paramters of the network, which completely misses…
shreyshnaccount on HN
Alternatives named
WaveNet autoregressive model
From 1 comment
You're using a pointwise loss, which means you are treating each timepoint as conditionally independent. That's a deeply flawed assumption, probabilistically. Try an…
rryan on HN