Second US Muon Collider Collaboration Meeting

Smartpixels: Testbench for a prototype ASIC implementing a neural network for on-detector data compression

Not scheduled

20m

University of Chicago

Poster

Speaker

Daniel Abadjiev (The University of Chicago)

Description

At a 10TeV muon collider, a high level of beam induced background (BIB) will overlay signal produced from muon collisions, similar to how pile-up at the HL-LHC will overlay signal from proton-proton collisions. On-detector differentiation of BIB from signal would improve performance of the inner pixel tracker. For the HL-LHC, we are developing a “smartpixel” application specific integrated circuit (ASIC) which implements a deep neural network on-chip for on-detector data compression and classification. We present testbench studies characterizing a prototype smartpixel ASIC and its potential application in the inner pixel tracker of a muon collider detector.

Presentation materials

USMCC_Poster.pdf