Tap a claim on the ring to put it at the centre.
← Understanding requires memory, so methods that boost memory often boost understanding too.
17 connected korrents · 18 moments from 13 May 2007 to 6 Oct 2026.
Everything filed under neural networks
neural networks
Everything filed under curiosity
curiosity
Everything filed under pruning
pruning
Everything filed under education
education
Everything filed under AI and human skill
AI and human skill Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Read this korrent: Understanding requires memory, so methods that boost memory often boost understanding too. Understanding requires memory, so methods that boost memory often boost understanding too. Last stated 3 weeks ago
6 Oct 2026
SY
Scott H. Young — holds since 2026-10-06 — tap for who they are
Same subject: The point of a good memory is not to remember more but to remember better, because forgetting most of what you experience is what human brains are built to do. — tap to centre the map on it The point of a good memory is not to remember more but to remember better, because forgetting most of what you experience is what human brains are built to do. Last stated 2 years ago
25 May 2024
CR
Charan Ranganath — holds since 2024-05-25 — tap for who they are
Same subject: Seeing something many times does not put it into memory: familiarity with a thing and knowledge of it are different, and people confuse the two constantly. — tap to centre the map on it Seeing something many times does not put it into memory: familiarity with a thing and knowledge of it are different, and people confuse the two constantly. Last stated 3 months ago
13 Jul 2026
AC
Alan Castel — holds since 2026-07-13 — tap for who they are
AC
Anne-Laure Le Cunff — holds since 2026-04-08 — tap for who they are
Same subject: Having both episodic and semantic memory is what lets a mind change on a dime without erasing what it already learned, and it is why humans can learn from so little data. — tap to centre the map on it Having both episodic and semantic memory is what lets a mind change on a dime without erasing what it already learned, and it is why humans can learn from so little data. Last stated 2 years ago
25 May 2024
CR
Charan Ranganath — holds since 2024-05-25 — tap for who they are
Same subject: Highlighting, rereading and summarising are poor ways to remember what you have read, and cramming is worse. — tap to centre the map on it Highlighting, rereading and summarising are poor ways to remember what you have read, and cramming is worse. Last stated 4 years ago
12 Jul 2022
AM
Adam Mastroianni — holds since 2022-07-12 — tap for who they are
Same subject: Solving a problem yourself, without searching or prompting, is a form of exercise -- the help makes you weaker. — tap to centre the map on it Solving a problem yourself, without searching or prompting, is a form of exercise -- the help makes you weaker. Last stated 8 months ago
3 Mar 2026
SY
Scott H. Young — holds since 2025-11-18 — tap for who they are
DS
Derek Sivers — holds since 2026-03-03 — tap for who they are
Same subject: Reading and listening are only preparation; learning happens by doing, and it consists of failing on the way to mastery. — tap to centre the map on it Reading and listening are only preparation; learning happens by doing, and it consists of failing on the way to mastery. Last stated 3 years ago
26 Mar 2024
SG
Seth Godin — holds since 2024-03-26 — tap for who they are
Same subject: An engineer writing business logic loses nothing by not understanding the layer underneath, exactly as they lose nothing by not managing memory. — tap to centre the map on it An engineer writing business logic loses nothing by not understanding the layer underneath, exactly as they lose nothing by not managing memory. Last stated 6 months ago
22 Apr 2026
MK
Martin Kleppmann — holds since 2026-04-22 — tap for who they are
Same subject: Forgetting names is not a defect of memory: a name is an arbitrary label with nothing to attach it to, and arbitrary material is exactly what brains are worst at. — tap to centre the map on it Forgetting names is not a defect of memory: a name is an arbitrary label with nothing to attach it to, and arbitrary material is exactly what brains are worst at. Last stated 2 years ago
25 May 2024
CR
Charan Ranganath — holds since 2024-05-25 — tap for who they are
Same subject: A small enough winning ticket learns faster than the network it was cut out of, and ends up more accurate than it. — tap to centre the map on it A small enough winning ticket learns faster than the network it was cut out of, and ends up more accurate than it. Last stated 9 years ago
9 Mar 2018
MC
Michael Carbin — holds since 2018-03-09 — tap for who they are
JF
Jonathan Frankle — holds since 2018-03-09 — tap for who they are
Same subject: A winning ticket wins on its initial weights: the connections it keeps started at values that happen to make training work. — tap to centre the map on it A winning ticket wins on its initial weights: the connections it keeps started at values that happen to make training work. Last stated 9 years ago
9 Mar 2018
MC
Michael Carbin — holds since 2018-03-09 — tap for who they are
JF
Jonathan Frankle — holds since 2018-03-09 — tap for who they are
Same subject: Batteries will replace transmission as the cheapest way to keep the lights on, and the grid will shrink rather than grow. — tap to centre the map on it Batteries will replace transmission as the cheapest way to keep the lights on, and the grid will shrink rather than grow. Last stated 11 months ago
8 Dec 2025
CH
Casey Handmer — holds since 2023-10-11 — tap for who they are
CH
Casey Handmer — holds since 2025-12-08 — tap for who they are
Same subject: A deep bidirectional model is strictly more powerful than a left-to-right model or a shallow concatenation of unidirectional models. — tap to centre the map on it A deep bidirectional model is strictly more powerful than a left-to-right model or a shallow concatenation of unidirectional models. Last stated 8 years ago
11 Oct 2018
KT
Kristina Toutanova — holds since 2018-10-11 — tap for who they are
MC
Ming-Wei Chang — holds since 2018-10-11 — tap for who they are
KL
Kenton Lee — holds since 2018-10-11 — tap for who they are
JD
Jacob Devlin — holds since 2018-10-11 — tap for who they are
Same subject: A layer should learn a residual with reference to its own input rather than an unreferenced function, which is what makes great depth trainable. — tap to centre the map on it A layer should learn a residual with reference to its own input rather than an unreferenced function, which is what makes great depth trainable. Last stated 11 years ago
10 Dec 2015
JS
Jian Sun — holds since 2015-12-10 — tap for who they are
KH
Kaiming He — holds since 2015-12-10 — tap for who they are
Same subject: A neural network's latent space is closer to an uncopyrightable syntax than to copyrightable expression. — tap to centre the map on it A neural network's latent space is closer to an uncopyrightable syntax than to copyrightable expression. Last stated 2 months ago
7 Sept 2026
KK
Kevin Kelly — holds since 2026-09-07 — tap for who they are
Same subject: A slot machine triggers the brain’s learning and curiosity pathways while teaching nothing, and that one-way exchange is what makes it contemptuous of the player. — tap to centre the map on it A slot machine triggers the brain’s learning and curiosity pathways while teaching nothing, and that one-way exchange is what makes it contemptuous of the player. Last stated 13 years ago
3 Jul 2013
RK
Raph Koster — holds since 2013-07-03 — tap for who they are
Same subject: Acquiring insight into how things work is a worthwhile effort in itself, not only for any payoff — tap to centre the map on it Acquiring insight into how things work is a worthwhile effort in itself, not only for any payoff Last stated 19 years ago
17 Oct 2007
PB
Peter Bevelin — holds since 2007-10-17 — tap for who they are
Same subject: Advancing in life depends more on what one learns later than on what one already knows — tap to centre the map on it Advancing in life depends more on what one learns later than on what one already knows Last stated 19 years ago
13 May 2007
CM
Charlie Munger — holds since 2007-05-13 — tap for who they are
At the centre
Understanding requires memory, so methods that boost memory often boost understanding too.
Holds Read this korrent →
The point of a good memory is not to remember more but to remember better, because forgetting most of what you experience is what human brains are built to do.
Holds
Seeing something many times does not put it into memory: familiarity with a thing and knowledge of it are different, and people confuse the two constantly.
Holds
Having both episodic and semantic memory is what lets a mind change on a dime without erasing what it already learned, and it is why humans can learn from so little data.
Holds
Highlighting, rereading and summarising are poor ways to remember what you have read, and cramming is worse.
Holds
Solving a problem yourself, without searching or prompting, is a form of exercise -- the help makes you weaker.
Holds
Reading and listening are only preparation; learning happens by doing, and it consists of failing on the way to mastery.
Holds
An engineer writing business logic loses nothing by not understanding the layer underneath, exactly as they lose nothing by not managing memory.
Holds
Forgetting names is not a defect of memory: a name is an arbitrary label with nothing to attach it to, and arbitrary material is exactly what brains are worst at.
Holds
A small enough winning ticket learns faster than the network it was cut out of, and ends up more accurate than it.
Holds
A winning ticket wins on its initial weights: the connections it keeps started at values that happen to make training work.
Holds
Batteries will replace transmission as the cheapest way to keep the lights on, and the grid will shrink rather than grow.
Holds
A deep bidirectional model is strictly more powerful than a left-to-right model or a shallow concatenation of unidirectional models.
Holds
A layer should learn a residual with reference to its own input rather than an unreferenced function, which is what makes great depth trainable.
Holds
A neural network's latent space is closer to an uncopyrightable syntax than to copyrightable expression.
Holds
A slot machine triggers the brain’s learning and curiosity pathways while teaching nothing, and that one-way exchange is what makes it contemptuous of the player.
Holds
Acquiring insight into how things work is a worthwhile effort in itself, not only for any payoff
Holds
Advancing in life depends more on what one learns later than on what one already knows
Holds