公开(公告)号：US20250094823A1

公开(公告)日：2025-03-20

申请号：US18368801

申请日：2023-09-15

Applicant: Cisco Technology, Inc.

Inventor： Myungjin Lee ,  Jayanth SRINIVASA ,  Ali PAYANI ,  Ramana Rao V.R. KOMPELLA

IPC: G06N3/098

Abstract: In one implementation, a controller determines performance of a partitioned neural network. The controller identifies, based on the performance, a particular partition of the partitioned neural network as a bottleneck. The controller configures a first device to execute a replica of the particular partition. The controller configures a multiplexer that provides an output of the particular partition or the replica of the particular partition as input to a downstream partition of the partitioned neural network.

公开(公告)号：US20250086971A1

公开(公告)日：2025-03-13

申请号：US18243819

申请日：2023-09-08

Applicant: Cisco Technology, Inc.

Inventor： Hugo Latapie ,  Enzo FENOGLIO ,  Viktoriya V. TSUKANOVA ,  Ramana Rao V. R. KOMPELLA ,  Joost BOTTENBLEY ,  Chiara TROIANI ,  Ali PAYANI ,  Johanna Wylie Lanier HARDY ,  Jayanth SRINIVASA

IPC: G06V20/40 ,  G06V10/774

Abstract: In one implementation, a device receives a request to generate a set of video clips that depict a specified classification label. The device represents each of one or more objects depicted in a particular video clip over time as a set of timeseries of key points associated with that object. The device makes a determination as to whether the particular video clip depicts the specified classification label by analyzing the set of timeseries of key points associated with the particular video clip and in accordance with one or more constraint parameters. The device labels, based on the determination, the particular video clip with the specified classification label for inclusion in the set of video clips that depict the specified classification label.

公开(公告)号：US20250036961A1

公开(公告)日：2025-01-30

申请号：US18227535

申请日：2023-07-28

Applicant: Cisco Technology, Inc.

Inventor： Myungjin Lee ,  Ganghua WANG ,  Ali PAYANI ,  Ramana Rao V. R. KOMPELLA

IPC: G06N3/098 ,  G06V10/764 ,  G06V10/774 ,  G06V10/776

Abstract: In one embodiment, a supervisory device in a federated learning system generates an aggregated model that aggregates a plurality of machine learning models trained by trainer nodes in a federated learning system during a training round. The supervisory device computes an accuracy loss metric for the aggregated model. The supervisory device also computes a fairness loss metric for the aggregated model based on fairness-related metrics associated with the plurality of machine learning models trained by the trainer nodes. The supervisory device initiates an additional training round during which the trainer nodes retrain their machine learning models for aggregation by the apparatus, in accordance with a constrained optimization problem that seeks to optimize a tradeoff between accuracy and fairness associated with the aggregated model.