Tap a claim on the ring to put it at the centre.
← More neurons allow more flexibility and complexity, but also take more time to build into a brain.
17 connected korrents · 13 moments from 10 Dec 2015 to 9 Sept 2026.
Everything filed under neural networks
neural networks
Everything filed under dementia
dementia
Everything filed under education
education
Everything filed under simplicity
simplicity
Everything filed under evolutionary biology
evolutionary biology
Everything filed under measuring intelligence
measuring intelligence
Everything filed under LLMs
LLMs
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: More neurons allow more flexibility and complexity, but also take more time to build into a brain.
More neurons allow more flexibility and complexity, but also take more time to build into a brain.
Last stated 3 years ago
3 Jun 2023
SH
Suzana Herculano-Houzel — holds since 2023-06-03 — tap for who they are
Same subject: The adult brain's stock of neurons is essentially fixed, and that is no limit on learning, because plasticity is the changing of connections between the cells you already have. — tap to centre the map on it
The adult brain's stock of neurons is essentially fixed, and that is no limit on learning, because plasticity is the changing of connections between the cells you already have.
Last stated 4 months ago
20 Jul 2026
TW
Tommy Wood — holds since 2026-07-20 — tap for who they are
Same subject: A testable hypothesis: more hippocampal neurons give a brain more resilience to withstand the damage that inevitably accumulates. — tap to centre the map on it
A testable hypothesis: more hippocampal neurons give a brain more resilience to withstand the damage that inevitably accumulates.
Last stated 3 years ago
3 Jun 2023
SH
Suzana Herculano-Houzel — holds since 2023-06-03 — tap for who they are
Same subject: Plotted against cortical neuron counts rather than brain size, birds overlap with primates: the more neurons, the more flexible the behaviour. — tap to centre the map on it
Plotted against cortical neuron counts rather than brain size, birds overlap with primates: the more neurons, the more flexible the behaviour.
Last stated 3 years ago
3 Jun 2023
SH
Suzana Herculano-Houzel — holds since 2023-06-03 — tap for who they are
Same subject: Learning takes time, effort and sometimes pain, and no tool changes that, because that is how the brain is built. — tap to centre the map on it
Learning takes time, effort and sometimes pain, and no tool changes that, because that is how the brain is built.
Last stated 3 months ago
10 Aug 2026
FL
Fei-Fei Li — holds since 2026-08-10 — tap for who they are
Same subject: Complexity has become a sport, as if making something more complicated showed you were better at it. — tap to centre the map on it
Complexity has become a sport, as if making something more complicated showed you were better at it.
Last stated 8 years ago
7 Sept 2018
JF
Jason Fried — holds since 2018-09-07 — tap for who they are
Same subject: If human cortical neurons tripled over two million years, humans gained not only cognitive capacity but a longer childhood. — tap to centre the map on it
If human cortical neurons tripled over two million years, humans gained not only cognitive capacity but a longer childhood.
Last stated 3 years ago
3 Jun 2023
SH
Suzana Herculano-Houzel — holds since 2023-06-03 — tap for who they are
Same subject: Intelligence is best defined practically as cognitive flexibility, which grows with the number of cortical neurons. — tap to centre the map on it
Intelligence is best defined practically as cognitive flexibility, which grows with the number of cortical neurons.
Last stated 3 years ago
3 Jun 2023
SH
Suzana Herculano-Houzel — holds since 2023-06-03 — tap for who they are
Same subject: More reasoning gives a language model more time and compute to solve harder problems, but increases latency and compute cost. — tap to centre the map on it
More reasoning gives a language model more time and compute to solve harder problems, but increases latency and compute cost.
Last stated a year ago
19 Aug 2025
JA
Jay Alammar — holds since 2025-08-19 — tap for who they are
Same subject: A curve, which is what a deep learning model is, is a very bad substrate for discrete computation. — tap to centre the map on it
A curve, which is what a deep learning model is, is a very bad substrate for discrete computation.
Last stated 2 years ago
6 Nov 2024
FC
François Chollet — holds since 2024-11-06 — 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 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: Intelligence is the execution of small, simplicity-weighted programs found by search over smooth loss landscapes in overparameterized networks, approaching Bayes-optimal reasoning as scale increases. — tap to centre the map on it
Intelligence is the execution of small, simplicity-weighted programs found by search over smooth loss landscapes in overparameterized networks, approaching Bayes-optimal reasoning as scale increases.
Last stated 5 years ago
11 Jun 2021
GW
Gwern — holds since 2021-06-11 — tap for who they are
Same subject: A transduction model can rely entirely on self-attention for input and output representations without sequence-aligned RNNs or convolution. — tap to centre the map on it
A transduction model can rely entirely on self-attention for input and output representations without sequence-aligned RNNs or convolution.
Last stated 9 years ago
12 Jun 2017
IP
Illia Polosukhin — holds since 2017-06-12 — tap for who they are
JU
Jakob Uszkoreit — holds since 2017-06-12 — tap for who they are
NP
Niki Parmar — holds since 2017-06-12 — tap for who they are
AV
Ashish Vaswani — holds since 2017-06-12 — tap for who they are
NS
Noam Shazeer — holds since 2017-06-12 — tap for who they are
AG
Aidan N. Gomez — holds since 2017-06-12 — tap for who they are
+2
2 more
Same subject: Linear probes are very strong classifiers, and attention-head probes are even stronger. — tap to centre the map on it
Linear probes are very strong classifiers, and attention-head probes are even stronger.
Last stated 11 months ago
20 Dec 2025
NN
Neel Nanda — holds since 2025-12-20 — tap for who they are
Same subject: Looped/recurrent-depth transformer architectures can improve model quality at a fixed compute budget when the model is large enough. — tap to centre the map on it
Looped/recurrent-depth transformer architectures can improve model quality at a fixed compute budget when the model is large enough.
Last stated 2 months ago
9 Sept 2026
SR
Sebastian Raschka — holds since 2026-09-09 — tap for who they are
same subject or similar wording a cloud: claims about one subject, named for it bar: when it was last stated, on a scale from 2015 to today — full is today a face: someone who holds the claim — tap it for who they are
At the centre
More neurons allow more flexibility and complexity, but also take more time to build into a brain.
Last stated 3 Jun 2023 · 3 years ago
Holds Suzana Herculano-Houzel
Read this korrent →
Similar wording
The adult brain's stock of neurons is essentially fixed, and that is no limit on learning, because plasticity is the changing of connections between the cells you already have.
Last stated 20 Jul 2026 · 4 months ago
Holds Tommy Wood
Similar wording
A testable hypothesis: more hippocampal neurons give a brain more resilience to withstand the damage that inevitably accumulates.
Last stated 3 Jun 2023 · 3 years ago
Holds Suzana Herculano-Houzel
Similar wording
Plotted against cortical neuron counts rather than brain size, birds overlap with primates: the more neurons, the more flexible the behaviour.
Last stated 3 Jun 2023 · 3 years ago
Holds Suzana Herculano-Houzel
Similar wording
Learning takes time, effort and sometimes pain, and no tool changes that, because that is how the brain is built.
Last stated 10 Aug 2026 · 3 months ago
Holds Fei-Fei Li
Similar wording
Complexity has become a sport, as if making something more complicated showed you were better at it.
Last stated 7 Sept 2018 · 8 years ago
Holds Jason Fried
Similar wording
If human cortical neurons tripled over two million years, humans gained not only cognitive capacity but a longer childhood.
Last stated 3 Jun 2023 · 3 years ago
Holds Suzana Herculano-Houzel
Similar wording
Intelligence is best defined practically as cognitive flexibility, which grows with the number of cortical neurons.
Last stated 3 Jun 2023 · 3 years ago
Holds Suzana Herculano-Houzel
Similar wording
More reasoning gives a language model more time and compute to solve harder problems, but increases latency and compute cost.
Last stated 19 Aug 2025 · a year ago
Holds Jay Alammar
Same subject: neural networks
A curve, which is what a deep learning model is, is a very bad substrate for discrete computation.
Last stated 6 Nov 2024 · 2 years ago
Holds François Chollet
Same subject: neural networks
A deep bidirectional model is strictly more powerful than a left-to-right model or a shallow concatenation of unidirectional models.
Last stated 11 Oct 2018 · 8 years ago
Holds Kristina Toutanova Ming-Wei Chang Kenton Lee Jacob Devlin
Same subject: neural networks
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 10 Dec 2015 · 11 years ago
Holds Jian Sun Kaiming He
Same subject: pruning
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 Mar 2018 · 9 years ago
Holds Michael Carbin Jonathan Frankle
Same subject: pruning
A winning ticket wins on its initial weights: the connections it keeps started at values that happen to make training work.
Last stated 9 Mar 2018 · 9 years ago
Holds Michael Carbin Jonathan Frankle
Same subject: pruning
Intelligence is the execution of small, simplicity-weighted programs found by search over smooth loss landscapes in overparameterized networks, approaching Bayes-optimal reasoning as scale increases.
Last stated 11 Jun 2021 · 5 years ago
Holds Gwern
Same subject: transformers
A transduction model can rely entirely on self-attention for input and output representations without sequence-aligned RNNs or convolution.
Last stated 12 Jun 2017 · 9 years ago
Holds Illia Polosukhin Jakob Uszkoreit Niki Parmar Ashish Vaswani Noam Shazeer Aidan N. Gomez Llion Jones Łukasz Kaiser
Same subject: transformers
Linear probes are very strong classifiers, and attention-head probes are even stronger.
Last stated 20 Dec 2025 · 11 months ago
Holds Neel Nanda
Same subject: transformers
Looped/recurrent-depth transformer architectures can improve model quality at a fixed compute budget when the model is large enough.
Last stated 9 Sept 2026 · 2 months ago
Holds Sebastian Raschka