ClaimsYann LeCun

“Many problems are difficult to represent with fixed-size tensors or variable-length sequences of tensors, but are better represented by graphs whose arcs and nodes are annotated by tensors.”

Yann LeCun 2019 ISSCC 2019 Plenary: Deep Learning Hardware: Past, Present and Future (yann.lecun.com)

Not checkable

Many problems are difficult to represent with fixed-size tensors or variable-length sequences of tensors, but are better represented by…

Not checkable An opinion, value judgement or statement with nothing to check.

Not checkable: An opinion, value judgement or statement with nothing to check. Not scored.

Cite this claim

Yann LeCun, “Many problems are difficult to represent with fixed-size tensors or variable-length sequences of tensors, but are better represented by…” (said 2019). Verdict: not checkable. Reliability API, claim c_35242a9b1b2b, method 0.1.0+c876030c, dataset release v1.1.2. https://epistacklabs.com/claims/c_35242a9b1b2b

This claim is in dataset release v1.1.2, with the same verdict.

Reply to this claim

For Yann LeCun, or someone speaking for them: a correction or counter-evidence. Replies are read before anything is shown; an approved reply shows your name, role, date, statement and link. Your email address is never shown and is deleted 30 days after the decision (privacy).

Verdicts are made automatically; how verdicts are made.