Jian Sun — everything, newest first

Jian Sun

Everything, newest first — across every channel. Their profile → · Subscribe

Sources

10 December 2015

Jian SunKorrents 10 Dec 2015

From one piece He, Zhang, Ren & Sun, "Deep Residual Learning for Image Recognition" (arXiv) 4 beliefs, in the piece's order there

korrents.com
The depth of a representation, not any particular architecture trick, is what most visual recognition tasks turn on.

Their words

The depth of representations is of central importance for many visual recognition tasks.

arxiv.org
korrents.com
Residual networks are easier to optimize than plain ones and keep gaining accuracy as depth increases.

neural networks

Their words

We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth.

arxiv.org
korrents.com
A layer should learn a residual with reference to its own input rather than an unreferenced function, which is what makes great depth trainable.

Their words

We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions.

arxiv.org

+ 1 more

korrents.com
Depth is not free: past a point, deeper neural networks are harder to train rather than simply better.

neural networks

Their words

Deeper neural networks are more difficult to train.

arxiv.org

What is a korrent?

A korrent is a belief a person has stated in their own words: one sentence stating the claim, backed by a quote and a source, kept at korrents.com.

Under a name here, the quoted block is what they actually said. The korrent beneath it is the claim those words support, in korrents' wording — tap it to see the record, its source, and who else holds it.

Nobody here wrote their own korrents. They are compiled from public statements, and a person can change their mind, which is recorded too.

About the English under a post

Some people here publish in a language other than English. Where they do, this site shows a machine translation beneath the post, in this typeface — the site's own, not theirs.

The post itself is never changed, moved or hidden: what is set in the serif above is exactly what the person published, and it is what to quote them on. A translation can be wrong in ways that matter, especially about tone.

Only the post's own words are translated. A quoted post, a linked article and a belief on korrents.com are left in their original language.