公开(公告)号：US20250095348A1

公开(公告)日：2025-03-20

申请号：US18368790

申请日：2023-09-15

Applicant: Cisco Technology, Inc.

Inventor： Myungjin Lee ,  Gustav Adrian Baumgart ,  Jaemin Shin ,  Ramana Rao V.R. Kompella

IPC: G06V10/82 ,  G06V10/771

Abstract: In one implementation, a device generates outputs of nodes in a upstream layer of a partitioned neural network. The device assigns priorities to each of the outputs of the nodes. The device selects, based on the priorities, a subset of the outputs to send to a remote device. The device sends, via a computer network, the subset of the outputs to the remote device for input to a downstream layer of the partitioned neural network.

公开(公告)号：US20240256890A1

公开(公告)日：2024-08-01

申请号：US18101620

申请日：2023-01-26

Applicant: Cisco Technology, Inc.

Inventor： Myungjin Lee ,  Dhruv Garg ,  Gaoxiang Luo ,  Ramana Rao V.R. Kompella

IPC: G06N3/098

CPC classification number: G06N3/098

Abstract: In one embodiment, a controller obtains state information from a plurality of nodes in a federated learning system. The controller determines, based on the state information, an adjustment to a topology of the federated learning system. The controller selects one or more nodes from among the plurality of nodes affected by the adjustment. The controller sends instructions to the one or more nodes, to implement the adjustment to the topology of the federated learning system.

公开(公告)号：US20250147956A1

公开(公告)日：2025-05-08

申请号：US18387278

申请日：2023-11-06

Applicant: Cisco Technology, Inc.

Inventor： Ali Payani ,  Ramana Rao V.R. Kompella

IPC: G06F16/2452 ,  G06F16/242

Abstract: In one embodiment, a method herein comprises: inputting, by a device, an input prompt to a first large language model to generate an output; computing, by the device, a reward metric in part by using a solver to process the output; tuning, by the device and based on the reward metric, a second large language model configured to correct errors of the first large language model using reinforcement learning; and using, by the device, the second large language model to correct an error of the first large language model.

公开(公告)号：US20230132213A1

公开(公告)日：2023-04-27

申请号：US17508241

申请日：2021-10-22

Applicant: Cisco Technology, Inc.

Inventor： Myungjin Lee ,  Ali Payani ,  Ramana Rao V.R. Kompella

IPC: G06N20/20

Abstract: In one embodiment, a device receives, from a plurality of training nodes that train a set of machine learning models using local training datasets, bias metrics associated with those machine learning models for each feature of the local training datasets. The device generates aggregated machine learning models over time that aggregate the machine learning models trained by the plurality of training nodes. The device constructs, based on the bias metrics, bias lineages for the aggregated machine learning models. The device provides, based on the bias lineages, a bias lineage for a particular one of the aggregated machine learning models for display.