Boltzmann Machines
AI
neural network examples
SHOW HN2017
201points
11comments
#160of 2,242 in 2017
Top 8%of 2017 by points
How HN took it
LovedMost comments that take a side are positive
4 positive, 2 neutral or asking, 0 mixed, 0 critical, out of 6 comments about the project. Thread score +0.50.
Execution: 3 for, 0 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
What people liked
Commenters call the work great and amazing
From 2 comments
I don't have any commentary here other than to say that this is great work!
iaw on HNOh...wow. This is amazing!
manjunaths on HN
Objections
RBMs are seldom used now; VAEs and GANs are preferred
From 2 comments
It was back then..we don't even support them in our framework anymore. Most folks use VAEs and GANs for generative models now. In general, they are just more stable.
agibsonccc on HNHow about DBN? It is also a generative model but why now rarely used? ML researchers following trends, like doing end-to-end CNN for whatever problems, and using this LSTM and…
mycat on HN
Questions
Why are RBMs seldom used anymore?
From 1 comment
Why are RBMs so seldom used? What is their weak point? Based on Hinton's talk I thought it was a major breakthrough back then.
visarga on HN
Alternatives named
Stacked autoencoders, VAEs and GANs
From 2 comments
A DBN is equivalently just stacked RBMs. Most folks just use stacked autoencoders for the exact same reasons you'd use a DBN. Most "off the shelf" work people do is fairly simple…
agibsonccc on HNIt was back then..we don't even support them in our framework anymore. Most folks use VAEs and GANs for generative models now. In general, they are just more stable.
agibsonccc on HN