Will there be a publicly explicated Scientific Theory of Deep Learning before 2032?
One-OffKIWissenschaft5JManifold MarketsKein KYCVerifizierte AuflösungsdatenOrdentlich kalibriertAktuelle Community-PrognoseNein 57.6%
Prognostiker
7
Fragetyp
binary
Methodik
Play-money forecasting platform
Quellentyp
Prognose
Marktdaten
Aktualisiert vor 6 Stunden
Veraltet2. Mai 26, 09:04 UTC31. Dez. 31, 23:59 UTC
Trends
Verwandte Märkte
Verwandte Fragen als Kontext, kein Vergleich gleichwertiger Kontrakte.
Will "The paper that killed deep learning theory" make the top fifty posts in LessWrong's 2026 Annual Review?
Manifold MarketsWill Gary Marcus still say that deep learning models can't reason after they prove the Riemann hypothesis?
Manifold MarketsWill geometric deep learning turn out to be as influential an idea as transformers?
Manifold MarketsWill Tamay Besiroglu win his Deep Learning vs Program Synthesis bet with Mike Knoop?
Manifold MarketsWill ANOTHER millennium prize problem be solved in 2026?
Manifold MarketsWhen will an AI lab solve another Millennium Prize Problem?
KalshiRegeln
A recent paper proposes an operationalization of a "Scientific Theory of Deep Learning," and argues that the field should indeed eventually admit a scientific theory.
- Though not the only possible form of a scientific theory, the paper considers the possibility that we will understand the mechanics of the learning process.
- Some desiderata they list for such a theory:
- Learning mechanics should be fundamental, proceeding logically from a first-principles description of neural network training.
- Interim assumptions about network weights, dynamics, and performance will be useful tools, but they should ultimately be explained from first principles.
- Learning mechanics should be mathematical, making unambiguous quantitative statements about important properties of neural networks.
