“We just like parameterized this with a small neural network and just searched over this decision-making network”

Machine Learning Street Talk (MLST) · What Most People Get Wrong About Evolution | Akarsh Kumar

Play from 26:51
26:51

Audio streams from the publisher’s own feed. Verbatim does not host or copy it.

What was described

parameterize flocking agents (Boyds) with a small neural network that decides direction based on neighbor positions, then search over network parameters

Said nearby on the same subject

“A neural network trained on companies that I happen to have liked in the past… could be used as a screen”
♫
Said on Australian Investors Podcast
Automation Share this moment
“…when the transformer came out, it was literally, as soon as the paper came out, literally the next day… it was clear… that transformers address the limitations of recurrent neural networks of learning long-term dependencies.”
♫
Said on Eye On A.I.
Why it worked Share this moment
“The easiest way for me to find AI-generated shows was by searching for the Quiet Please Network.”
♫
Said on Shell Game
How they work Share this moment
“You should create a guest network that's separate from your main network at home and how that can improve your cybersecurity”
MP
Mike Piper
The Long View ·
Growth tactic Share this moment

Moments like this, every Monday

The strongest new moments on your topics, in the speakers' own words. Free for three topics.

No card. No password. One-click unsubscribe.

Track a competitor?

Pro watches up to 25 names or phrases and emails you the morning after they are said.

See Pro, $29 a month

Verbatim quotes a short extract and links to the episode; the episode belongs to its publisher. Remove a show.