The Platonic Representation Hypothesis

  Рет қаралды 4,649

MITCBMM

MITCBMM

Күн бұрын

Пікірлер: 18
@doublepinger
@doublepinger 3 ай бұрын
The part at the end about a blind person being given sight - as far as I'm aware, blind people given sight still end up using their cane. The "simple" obstacle of a curb is very foreign to them, by sight.
@coda-n6u
@coda-n6u 3 ай бұрын
Do they use the cane indefinitely?
@andrewferguson6901
@andrewferguson6901 3 ай бұрын
The discussion around 48:30 is literally textbook perfection example of the scientific method. It's an observation, question, and testable hypothesis that follows from your understanding of the topic, but has not yet been tested. *chef's kiss*
@BBeu-i6t
@BBeu-i6t 3 ай бұрын
Thank you 🙏 ❤
@nathangonzales-hess6569
@nathangonzales-hess6569 3 ай бұрын
what are these surname bots about?
@ArielTavori
@ArielTavori 3 ай бұрын
Right? Disturbing. All in sets of six. Smells like cryptography / data tagging / state actor.
@nathangonzales-hess6569
@nathangonzales-hess6569 2 ай бұрын
@@ArielTavori I came across a video where someone guessed that it's a technique to doxx channel owners by probing their banned words lists. --The idea being that the owner might include their legal name in the list.
@mslapik
@mslapik 3 ай бұрын
As humans, we've built physical monuments to represent our abstract ideas. Concepts like universities, companies, and countries-while abstract-are embodied by physical structures in the world. Could a vision model, then, use these physical objects to learn about the abstract concepts they represent?
@coda-n6u
@coda-n6u 3 ай бұрын
I feel like this has already happened. Ex. if you ask a generative model to show you "freedom of the press", it will come up with images related to journalism, like news papers, or images related to freedom, like an uncaged bird or something. It's inherently an analogy, but one that is pre-trained on human analogies.
@NetworkCathedral
@NetworkCathedral 2 ай бұрын
if it were given simpler concepts to build them out of, 100% yes.
@AlgoNudger
@AlgoNudger 3 ай бұрын
Thanks.
@janerikbellingrath820
@janerikbellingrath820 3 ай бұрын
super interesting
@angelorf
@angelorf 3 ай бұрын
Very clear lecture. Thanks for this! Seems to me you are throwing a lot of engineering and science against a problem which is fundamentally philosophical. Assuming that our senses observe aspects of the real world is a necessary prerequisite for doing science and it is similarly a prerequisite for machine learning to have any use. It doesn't require empirical validation. The hypothesis aligns better with Aristotles philosophy than with Platos. If you ask me to which image the snake source image is more similar, the black snake or the closeup of a snake then I would say your question is unclear. What does that experiment tell us about how humans tend to interpret an unclear objective? Very nice work at the intersection between my two studies: philosophy and artificial intelligence.
@rysw19
@rysw19 3 ай бұрын
This is extremely interesting research, but the conclusions are fundamentally flawed. We build these systems with all kinds of priors based on our own capabilities, then we judge their effectiveness in relation to our own objectives. The models are reflections of ourselves first and foremost, and any relation they have to the world is mediated by the connection we have with the world.
@richardnunziata3221
@richardnunziata3221 3 ай бұрын
Has attention and saliency been consider in these
@blengi
@blengi 3 ай бұрын
hmmm, this AI stuff seems a bit isomorphic to my information agnostic abiogenesis matrix model, which for various reasons kind of implies exist an ecology of universal latent space representations via auto selection over entropic information compactification.. Even hypothesized similarly in an AI LLM context about _platonic information representations forms convergently arrived at_ elsewhere ie before this paper. Maybe they read lol?
@HopkinsDean-r8i
@HopkinsDean-r8i 3 ай бұрын
Walker David Rodriguez Timothy Wilson Robert
@MalachiSpring-s1t
@MalachiSpring-s1t 3 ай бұрын
Gonzalez Sharon Hernandez Jessica Hernandez Edward
Towards Understanding Deep Classifiers though Neural Collapse
1:04:52
Hippocampal memory, cognition, and the role of sleep - part 1
1:10:07
Леон киллер и Оля Полякова 😹
00:42
Канал Смеха
Рет қаралды 4,7 МЛН
Каха и дочка
00:28
К-Media
Рет қаралды 3,4 МЛН
Why Smart Groups Fail and Misfits Win
21:08
Artificially Aware
Рет қаралды 1,6 М.
The Simple Math Problem That Revolutionized Physics
32:44
Veritasium
Рет қаралды 8 МЛН
Learning to Reason, Insights from Language Modeling
57:43
MITCBMM
Рет қаралды 6 М.
The Riemann Hypothesis, Explained
16:24
Quanta Magazine
Рет қаралды 6 МЛН
The moment we stopped understanding AI [AlexNet]
17:38
Welch Labs
Рет қаралды 1,4 МЛН
21. Chaos and Reductionism
1:37:33
Stanford
Рет қаралды 1,7 МЛН
The Key Equation Behind Probability
26:24
Artem Kirsanov
Рет қаралды 158 М.
Hippocampal memory, cognition, and the role of sleep - part 2
1:22:30
MIT 6.S191: Reinforcement Learning
1:00:19
Alexander Amini
Рет қаралды 64 М.
Леон киллер и Оля Полякова 😹
00:42
Канал Смеха
Рет қаралды 4,7 МЛН