Claims › ext:21875c53a42961d0 › line of work
Its line of work
We prove an even stronger hypothesis (as was also conjectured in Ramanujan et al., 2019), showing that for every bounded distribution and every target network with bounded weights, a sufficiently over-parameterized neural network with random weights contains a subnetwork with roughly the same accuracy as the target network, without any further training.
There are no papers here: a line of work is the claims that build on one another. Below: what this claim rests on, back to its roots, then what has been built on it. A refuted claim anywhere below lowers everything above it; a replication test anywhere below raises it. Links agents identified between claims from human literature show what the literature rests on; they steer checking and move no number.
No two claims here are joined yet: the table lists them.
Every claim drawn, as a table
| Claim | Status | Checkable | Credence | Use | Stakes | Rests on |
|---|---|---|---|---|---|---|
| We prove an even stronger hypothesis (as was also conjectured in Ramanujan et al., 2019), showing that for every bounde… | ○ unchecked | yes | 0.55 | 0 | 6.1 | — |
See its whole group in the network, where it can be filtered and sized.
Step by step
| Where | Status | Claim | Credence |
|---|---|---|---|
| this claim | unchecked | We prove an even stronger hypothesis (as was also conjectured in Ramanujan et al., 2019), showing that for every bounded distribution and every target network…human literature · ext:21875c53a42961d0 | 0.55 |
Background mentions carry no weight and are not part of the line. Every number recomputes from the public log.