# US 10,872,292 B1 · Compact neural networks using condensed filters > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,872,292 B1 - Document ID: US10872292B1 - Status: Granted - Kind: B1 - Application number: 16/155,656 - Filed: 2018-10-09 - Granted: 2020-12-22 - Earliest claimed: 2017-10-09 - Assignees: Snap Inc. - Applicants: Yingzhen Yang; Jianchao Yang; Ning Xu - Inventors: Yingzhen Yang; Jianchao Yang; Ning Xu - Web page: https://patentgrep.com/patent/US10872292B1 ## CPC - G06N 3/04: Architecture, e.g. interconnection topology - G06N 3/045: Combinations of networks - G06N 3/0464: Convolutional networks [CNN, ConvNet] - G06N 3/0495: Quantised networks; Sparse networks; Compressed networks - G06T 5/20: using local operators - G06T 7/10: Segmentation; Edge detection (motion-based segmentation G06T7/215) - G06N 3/08: Learning methods - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ## Abstract A compact neural network system can generate multiple individual filters from a compound filter. Each convolutional layer of a convolutional neural network can include a compound filters used to generate individual filters for that layer. The individual filters overlap in the compound filter and can be extracted using a sampling operation. The extracted individual filters can share weights with nearby filters thereby reducing the overall size of the convolutional neural network. ## Claims ### Claim 1 A method comprising: generating, using one or more processors of a machine, an image; generating, from a compound neural network filter, a plurality of additional filters, wherein the plurality of additional filters are kernels of a convolution layer in a convolutional neural network; generating, using the convolutional neural network, a modified image from the image, the convolutional neural network configured to generate the modified image by applying the plurality of additional filters to the image; and causing the modified image to be displayed on a network site. ### Claim 2 (depends on 1) The method of claim 1, wherein the plurality of additional filters are generated by sampling the compound neural network filter. ### Claim 3 (depends on 2) The method of claim 2, wherein the plurality of additional filters overlap in the compound neural network filter. ### Claim 4 (depends on 1) The method of claim 1, wherein the plurality of additional filters share weights. ### Claim 5 (depends on 1) The method of claim 1, wherein the convolutional neural network comprises a plurality of convolution layers, each convolution layer having a corresponding compound neural network filter configured to generate a plurality of individual filters for that convolution layer, the plurality of convolution layers comprising the convolution layer. ### Claim 6 (depends on 5) The method of claim 5, further comprising: generating, for each of the convolution layers, a set of additional filters from a corresponding compound filter. ### Claim 7 (depends on 1) The method of claim 1, wherein at least one of the plurality of additional filters is generated using a rotation operation. ### Claim 8 (depends on 1) The method of claim 1, wherein at least one of the plurality of additional filters is generated using a reflection operation. ### Claim 9 (depends on 1) The method of claim 1, wherein the convolutional neural network is configured to perform image segmentation. ### Claim 10 (depends on 1) The method of claim 1, wherein the convolutional neural network is configured to perform image style transfer. ### Claim 11 (depends on 1) The method of claim 1, wherein the modified image is published as an ephemeral message on the network site. ### Claim 12 A system comprising: one or more processors of a machine; and a memory storing instructions that, when executed by the one or more processors, cause the machine to perform operations comprising: generating, using one or more processors of a machine, an image; generating, from a compound neural network filter, a plurality of additional filters, wherein the plurality of additional filters are kernels of a convolution layer in a convolutional neural network; generating, using the convolutional neural network, a modified image from the image, the convolutional neural network configured to generate the modified image by applying the plurality of additional filters to the image; and causing the modified image to be displayed on a network site. ### Claim 13 (depends on 12) The system of claim 12, wherein the plurality of additional filters are generated by sampling the compound neural network filter. ### Claim 14 (depends on 13) The system of claim 13, wherein the plurality of additional filters overlap in the compound neural network filter. ### Claim 15 (depends on 12) The system of claim 12, wherein the plurality of additional filters share weights. ### Claim 16 (depends on 12) The system of claim 12, wherein the convolutional neural network comprises a plurality of convolution layers, each convolution layer having a corresponding compound neural network filter configured to generate a plurality of individual filters for that convolution layer, the plurality of convolution layers comprising the convolution layer. ### Claim 17 A machine-readable storage device embodying instructions that, when executed by a machine, cause the machine to perform operations comprising: generating, using one or more processors of a machine, an image; generating, from a compound neural network filter, a plurality of additional filters, wherein the plurality of additional filters are kernels of a convolution layer in a convolutional neural network; generating, using the convolutional neural network, a modified image from the image, the convolutional neural network configured to generate the modified image by applying the plurality of additional filters to the image; and causing the modified image to be displayed on a network site. ### Claim 18 (depends on 17) The machine-readable storage device of claim 17, wherein the plurality of additional filters are generated by sampling the compound neural network filter.