US2022414473A1PendingUtilityA1
Learning device unit
Est. expiryJun 8, 2035(~8.8 yrs left)· nominal 20-yr term from priority
G06N 3/045G06N 3/04G06N 3/08G06N 3/0454G06N 20/00G06N 3/098G06N 3/0499G06N 3/09
68
PatentIndex Score
0
Cited by
0
References
0
Claims
Abstract
[Problem] To provide a learning device for performing more efficient machine learning.[Solution] A learning device unit according to one embodiment comprises at least one learning device and a connection device for connecting an intermediate learning device having an internal state shared by another learning device unit to the at least one learning device.
Claims
exact text as granted — not AI-modifiedWe claim:
1 . An apparatus comprising:
at least one memory storing therein an intermediate neural network model; and at least one processor configured to execute said intermediate neural network model, wherein said intermediate neural network model is respectively inputted:
first information based on information outputted by a first neural network model included in a first machinery which is based on information from a first sensor included in said first machinery, wherein said first machinery incorporates said first sensor, a first memory storing said first neural network model, and a first processor configured to execute said first neural network model; and
second information based on information outputted by a third neural network model included in a second machinery which is based on information from a second sensor included in said second machinery, wherein said second machinery incorporates said second sensor, a second memory storing said third neural network model, and a second processor configured to execute said third neural network model;
wherein said first and second memories are distinct from said at least one memory, and said first and second processors are distinct from said at least one processor;
wherein said apparatus, said first machinery and said second machinery are different from each other; and
wherein said at least one processor is configured to execute said intermediate neural network model, so that said intermediate neural network model is at least capable of outputting information based on either (i) inputting said first information via a first connection from said first machinery to said apparatus or (ii) inputting said second information via a second connection from said second machinery to said apparatus.Join the waitlist — get patent alerts
Track US2022414473A1 — get alerts on status changes and closely related new filings.
We store only your email — no account needed. See our privacy policy.