# US 2025/0095348 A1 · Communication-aware inference serving for partitioned neural networks > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2025/0095348 A1 - Document ID: US20250095348A1 - Status: Published application - Kind: A1 - Application number: 18/368,790 - Filed: 2023-09-15 - Published: 2025-03-20 - Earliest claimed: 2023-09-15 - Assignees: Cisco Technology, Inc. - Applicants: Cisco Technology, Inc. - Inventors: Myungjin Lee; Gustav Adrian Baumgart; Jaemin Shin; Ramana Rao V.R. Kompella - Web page: https://patentgrep.com/patent/US20250095348A1 ## CPC - G06V 10/82: using neural networks - G06V 10/771: Feature selection, e.g. selecting representative features from a multi-dimensional feature space - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## 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. ## Claims ### Claim 1 A method comprising: generating, by a device, outputs of nodes in an upstream layer of a partitioned neural network; assigning, by device, priorities to each of the outputs of the nodes; selecting, by the device and based on the priorities, a subset of the outputs to send to a remote device; and sending, by the device and via a computer network, the subset of the outputs to the remote device for input to a downstream layer of the partitioned neural network. ### Claim 2 (depends on 1) The method as in claim 1, wherein the device selects the subset of the outputs to send to the remote device based further on a latency associated with a path between the device and the remote device in the computer network. ### Claim 3 (depends on 2) The method as in claim 2, further comprising: opting, by the device, to send all outputs of the nodes in the upstream layer to the remote device when the latency is below a threshold. ### Claim 4 (depends on 1) The method as in claim 1, further comprising: performing knockout to determine accuracy losses associated with blocking outputs of each of the nodes in the upstream layer of the partitioned neural network. ### Claim 5 (depends on 4) The method as in claim 4, wherein the priorities are based on the accuracy losses. ### Claim 6 (depends on 1) The method as in claim 1, wherein the partitioned neural network is configured to analyze sensor data captured by one or more sensors in the computer network. ### Claim 7 (depends on 6) The method as in claim 6, wherein the sensor data comprises video data captured by one or more cameras in the computer network. ### Claim 8 (depends on 1) The method as in claim 1, wherein the priorities are based on a mean and standard deviation of the outputs of the nodes in the upstream layer. ### Claim 9 (depends on 1) The method as in claim 1, wherein the device selects the subset of the outputs to send to the remote device based on one or more policies. ### Claim 10 (depends on 1) The method as in claim 1, further comprising: inputting, by the device, outputs of a prior layer of the partitioned neural network to the upstream layer of the partitioned neural network. ### Claim 11 An apparatus, comprising: a network interface to communicate with a computer network; a processor coupled to the network interface and configured to execute one or more processes; and a memory configured to store a process that is executed by the processor, the process when executed configured to: generate outputs of nodes in an upstream layer of a partitioned neural network; assign priorities to each of the outputs of the nodes; select, based on the priorities, a subset of the outputs to send to a remote device; and send, via a computer network, the subset of the outputs to the remote device for input to a downstream layer of the partitioned neural network. ### Claim 12 (depends on 11) The apparatus as in claim 11, wherein the apparatus selects the subset of the outputs to send to the remote device based further on a latency associated with a path between the apparatus and the remote device in the computer network. ### Claim 13 (depends on 12) The apparatus as in claim 12, wherein the process when executed is further configured to: opt to send all outputs of the nodes in the upstream layer to the remote device when the latency is below a threshold. ### Claim 14 (depends on 11) The apparatus as in claim 11, wherein the process when executed is further configured to: perform knockout to determine accuracy losses associated with blocking outputs of each of the nodes in the upstream layer of the partitioned neural network. ### Claim 15 (depends on 14) The apparatus as in claim 14, wherein the priorities are based on the accuracy losses. ### Claim 16 (depends on 11) The apparatus as in claim 11, wherein the partitioned neural network is configured to analyze sensor data captured by one or more sensors in the computer network. ### Claim 17 (depends on 16) The apparatus as in claim 16, wherein the sensor data comprises video data captured by one or more cameras in the computer network. ### Claim 18 (depends on 11) The apparatus as in claim 11, wherein the priorities are based on a mean and standard deviation of the outputs of the nodes in the upstream layer. ### Claim 19 (depends on 11) The apparatus as in claim 11, wherein the apparatus and the remote device are edge devices in the computer network. ### Claim 20 A tangible, non-transitory, computer-readable medium storing program instructions that cause a device in a computer network to execute a process comprising: generating, by the device, outputs of nodes in an upstream layer of a partitioned neural network; assigning, by device, priorities to each of the outputs of the nodes; selecting, by the device and based on the priorities, a subset of the outputs to send to a remote device; and sending, by the device and via the computer network, the subset of the outputs to the remote device for input to a downstream layer of the partitioned neural network.