# US 2020/0394401 A1 · Visually focused first-person neural network interpretation > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2020/0394401 A1 - Document ID: US20200394401A1 - Status: Published application - Kind: A1 - Application number: 16/515,751 - Filed: 2019-07-18 - Published: 2020-12-17 - Earliest claimed: 2019-06-13 - Assignees: International Business Machines Corporation - Applicants: International Business Machines Corporation - Inventors: Aaron K. BAUGHMAN; Gopal Sarma PINGALI; Maria del Pilar BELINCHON BALLESTA; Craig M. TRIM - Web page: https://patentgrep.com/patent/US20200394401A1 ## CPC - G06N 3/08: Learning methods - G06F 17/15: Correlation function computation {including computation of convolution operations (arithmetic circuits for sum of products per se, e.g. multiply-accumulators G06F7/5443; digital filters, e.g. FIR, IIR, adaptive filters H03H17/00)} - G06F 17/18: for evaluating statistical data {, e.g. average values, frequency distributions, probability functions, regression analysis (forecasting specially adapted for a specific administrative, business or logistic context G06Q10/04)} - G06F 18/24: Classification techniques - G06N 3/045: Combinations of networks - G06N 3/0464: Convolutional networks [CNN, ConvNet] - G06N 3/047: Probabilistic or stochastic networks - G06N 3/09: Supervised learning - G06V 10/764: using classification, e.g. of video objects - G06V 10/82: using neural networks - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract Methods and systems for visually focused first-person neural network interpretation are disclosed. A method includes: receiving, by a computing device, an image; determining, by the computing device, feature vectors from the image; determining, by the computing device, a first padding value and a first stride value by inputting the feature vectors into a deep neural network; determining, by the computing device, a second padding value and a second stride value by inputting the feature vectors into at least one multiple regression model; determining, by the computing device, padding by averaging the first padding value and the second padding value; determining, by the computing device, stride by averaging the first stride value and the second stride value; and classifying, by the computing device, the image using a convolutional neural network using the padding and the stride. ## Claims ### Claim 1 A method comprising: receiving, by a computing device, an image; determining, by the computing device, feature vectors from the image; determining, by the computing device, a first padding value and a first stride value by inputting the feature vectors into a deep neural network; determining, by the computing device, a second padding value and a second stride value by inputting the feature vectors into at least one multiple regression model; determining, by the computing device, padding by averaging the first padding value and the second padding value; determining, by the computing device, stride by averaging the first stride value and the second stride value; and classifying, by the computing device, the image using a convolutional neural network using the padding and the stride. ### Claim 2 (depends on 1) The method according to claim 1, wherein the computing device receives the image from a mobile device. ### Claim 3 (depends on 1) The method according to claim 1, wherein the feature vectors include a feature vector of a person in the image and a feature vector of an object in the image. ### Claim 4 (depends on 1) The method according to claim 1, further comprising training, by the computing device, the deep neural network using a training data set including descriptors and corresponding padding and stride values. ### Claim 5 (depends on 1) The method according to claim 1, further comprising training, by the computing device, the at least one multiple regression model using a training data set including descriptors and corresponding padding and stride values. ### Claim 6 (depends on 1) The method according to claim 1, further comprising masking, by the computing device, a portion of the image. ### Claim 7 (depends on 6) The method according to claim 6, wherein the classifying the image using the convolutional neural network comprises convolving a filter across the masked portion of the image. ### Claim 8 A computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computing device to cause the computing device to: train a neural network modeling padding and stride, a regression model for padding, and a regression model for stride using a training data set including descriptors and corresponding padding and stride values; receive an image; determine a first padding value and a first stride value using the image and the neural network modeling padding and stride; determine a second padding value using the image and the regression model for padding; determine a second stride value using the image and the regression model for stride; determine padding by averaging the first padding value and the second padding value; determine stride by averaging the first stride value and the second stride value; and classify the image using a convolutional neural network using the padding and the stride. ### Claim 9 (depends on 8) The computer program product according to claim 8, wherein the image is received from a mobile device. ### Claim 10 (depends on 8) The computer program product according to claim 8, the program instructions further being executable by the computing device to cause the computing device to determine feature vectors from the image. ### Claim 11 (depends on 10) The computer program product according to claim 10, wherein the determining the first padding value and the first stride value comprises inputting the feature vectors into the neural network modeling padding and stride. ### Claim 12 (depends on 10) The computer program product according to claim 10, wherein the determining the second padding value comprises inputting the feature vectors into the regression model for padding, and the determining the second stride value comprises inputting the feature vectors into the regression model for stride. ### Claim 13 (depends on 10) The computer program product according to claim 10, wherein the feature vectors include a feature vector of a person in the image and a feature vector of an object in the image. ### Claim 14 (depends on 8) The computer program product according to claim 8, the program instructions further being executable by the computing device to cause the computing device to mask a portion of the image. ### Claim 15 (depends on 14) The computer program product according to claim 14, wherein the classifying the image using the convolutional neural network comprises convolving a filter across the masked portion of the image. ### Claim 16 A system comprising: a hardware processor, a computer readable memory, and a computer readable storage medium associated with a computing device; program instructions to receive an image; program instructions to determine feature vectors from the image; program instructions to determine a first padding value and a first stride value by inputting the feature vectors into a deep neural network; program instructions to determine a second padding value and a second stride value by inputting the feature vectors into at least one multiple regression model; program instructions to determine padding by averaging the first padding value and the second padding value; program instructions to determine stride by averaging the first stride value and the second stride value; and program instructions to classify the image using a convolutional neural network using the padding and the stride, wherein the program instructions are stored on the computer readable storage medium for execution by the hardware processor via the computer readable memory. ### Claim 17 (depends on 16) The system according to claim 16, wherein the feature vectors include a feature vector of a person in the image and a feature vector of an object in the image. ### Claim 18 (depends on 16) The system according to claim 16, further comprising program instructions to train the deep neural network using a training data set including descriptors and corresponding padding and stride value. ### Claim 19 (depends on 16) The system according to claim 16, further comprising program instructions to train the at least one multiple regression model using a training data set including descriptors and corresponding padding and stride values. ### Claim 20 (depends on 16) The system according to claim 16, further comprising program instructions to mask a portion of the image, wherein the classifying the image using the convolutional neural network comprises convolving a filter across the masked portion of the image.