Viewing profile — mannigfaltig
mannigfaltig
HN member- Joined
- Sat, Mar 04, 2017, 11:54 PM UTC
- HN karma
- 386
- Public activity
- 111 items
- HN profile
- View on Hacker News ↗
About mannigfaltig
No profile information was provided.
Recent public activity
- story
-
comment
Comment #15615020
In their second publication they actually use the probabilistic unit, but computing those requires running an EM algorithm for each layer of capsules: https://openreview.net/forum?…
-
comment
Comment #15600559
I doubt this will be a real problem because I've seen brilliant people excel in provincial universities with very little means and talent around. Internet education has gotten pret…
-
comment
Comment #15593409
I still find it incredibly hard to tell whether this is overblown hype or legit scientific progress. There is no indication whatsoever that this approach scales to deep feature hie…
-
comment
Comment #15592246
My guess would be that symmetry is a simple heuristic measure of physical fitness. Visual attraction is basically a strong regularizer that restricts the search space to phenotypes…
-
comment
Comment #15586315
The problem is that anxiety is warranted in this case. You can’t do anything about solving the problem for everybody, but you can potentially save your own life: - Work like a madm…
-
comment
Comment #15582772
> evolution of evolvability and then a seemingly unrelated subject: the evolution of robustness. Isn't evolvability only about robustness? What other criteria would improve evoluti…
-
comment
Comment #15582730
I think, the main effect of sexual reproduction is that, much like GANs and competitive self-play, it creates species-internal competition: Both sexes need to impress, which makes …
- story
-
comment
Comment #15579396
That seems like a strange/unnecessary way to put it because DO is noise.
-
comment
Comment #15579077
You can also call it just subgraph; not all of them, but exponentially many.
-
comment
Comment #15579015
Wait, that can’t be wrong because that is literally what DO does. It is a convex hull regularizer around the network activations using noise. That is also why dropout does not solv…
-
comment
Comment #15574691
Actually, GANs reach state of the art in anomaly/outlier detection and drug/molecule prediction, so there is certainly more to it than just artistic applications: https://openrevie…
- comment
- comment
- comment
-
comment
Comment #15552304
Totalitarian systems are quicker to come up with the rules (in this case for self-preservation). And when time matters, then it has obvious advantages.
-
comment
Comment #15540632
How is Assange Putin’s mouthpiece?
- comment
-
comment
Comment #15535957
Small correction: Learning algorithms that determine the contribution of a unit to the result over time can also be local in time, namely by tracking the contributions online (for …
-
comment
Comment #15534050
> By firing earlier it inhibits neighboring cells, creating highly sparse patterns of activity for correctly predicted inputs. This part is so vague. It seems to lack an explanatio…
- comment
-
comment
Comment #15516969
The same actually happened in Spain 400 years ago. There used to be a lot of forests in Spain: http://m.dw.com/en/spain-replants-after-centuries-of-defores...
- comment
-
comment
Comment #15505891
I guess deep world models are still severely riddled by all sorts of problems: vanishing gradients, BPTT being O(T), poor generalization ability of NNs (which likely is due to the …