Will there be a publicly explicated Scientific Theory of Deep Learning before 2032?
One-OffAIWetenschap5jManifold MarketsGeen KYCGeverifieerde afwikkelingsgegevensGoed gekalibreerdHuidige gemeenschapsvoorspellingNee 57.6%
Voorspellers
7
Vraagtype
binary
Methodologie
Play-money forecasting platform
Brontype
Voorspelling
Marktdata
Bijgewerkt 10 uur geleden
Verouderd2 mei 26, 09:04 UTC31 dec 31, 23:59 UTC
Trends
Gerelateerde Markten
Gerelateerde vragen voor context, geen vergelijking van gelijkwaardige contracten.
By EOY 2026, will it seem as if deep learning hit a wall by EOY 2025?
Manifold MarketsWill the first AGI be built mostly within the deep learning paradigm?
Manifold MarketsWill "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 ANOTHER millennium prize problem be solved in 2026?
Manifold MarketsWhat [mathematical statement] will happen by [date]?
Manifold MarketsRegels
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.
