# US 2019/0377848 A1 · Coordinates-based variational autoencoder for generating synthetic via layout patterns > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2019/0377848 A1 - Document ID: US20190377848A1 - Status: Published application - Kind: A1 - Application number: 16/001,531 - Filed: 2018-06-06 - Published: 2019-12-12 - Earliest claimed: 2018-06-06 - Assignees: International Business Machines Corporation - Applicants: International Business Machines Corporation - Inventors: Jing Sha; Michael A. Guillorn; Derren N. Dunn - Web page: https://patentgrep.com/patent/US20190377848A1 ## CPC - G06F 30/398: Design verification or optimisation, e.g. using design rule check [DRC], layout versus schematics [LVS] or finite element methods [FEM] (optical proximity correction [OPC] design processes G03F1/36) - G06N 3/042: Knowledge-based neural networks; Logical representations of neural networks - G06N 3/0455: Auto-encoder networks; Encoder-decoder networks - G06N 3/047: Probabilistic or stochastic networks - G06N 3/0475: Generative networks - G06N 3/08: Learning methods - G06N 3/09: Supervised learning - G06F 2111/02: CAD in a network environment, e.g. collaborative CAD or distributed simulation - G06F 2111/20: Configuration CAD, e.g. designing by assembling or positioning modules selected from libraries of predesigned modules - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract A method is presented for generating a plurality of physical design layout patterns. The method includes selecting one or more physical design layouts for neural network training, converting the plurality of physical design layout patterns into coordinate arrays, a coordinate array of the coordinate arrays including via center coordinates of vias in a physical design layout pattern of the plurality of physical design layout patterns, training, by employing the coordinate arrays, a variational autoencoder (VAE), and generating one or more new synthetic coordinate arrays by employing the trained VAE, a synthetic coordinate array of the one or more new synthetic coordinate arrays including via center coordinates of vias for a new physical design layout pattern. ## Claims ### Claim 1 A method for generating a plurality of physical design layout patterns, the method comprising: selecting one or more physical design layouts for neural network training; converting the plurality of physical design layout patterns into coordinate arrays, a coordinate array of the coordinate arrays including via center coordinates of vias in a physical design layout pattern of the plurality of physical design layout patterns; training, by employing the coordinate arrays, a variational autoencoder (VAE); and generating one or more new synthetic coordinate arrays by employing the trained VAE, a synthetic coordinate array of the one or more new synthetic coordinate arrays including via center coordinates of vias for a new physical design layout pattern. ### Claim 2 (depends on 1) The method of claim 1, wherein the coordinate array has a size of M*N, where M is a number of values for representing center coordinates of respective ones of features in a designated coordinate system and N is a maximum number of vias in a field of view of the physical design layout pattern represented by the physical design layout pattern. ### Claim 3 (depends on 2) The method of claim 2, wherein, when the field of view includes fewer than N vias, the coordinate array is padded with null values outside a range of possible coordinates for the field of view of the physical design layout pattern. ### Claim 4 (depends on 1) The method of claim 1, wherein the vias of the one or more new synthetic coordinate arrays include fixed-size rectangular features. ### Claim 5 (depends on 4) The method of claim 4, wherein the coordinate array includes designated entries for coordinates of respective ones of the centers of the fixed-size rectangular features. ### Claim 6 (depends on 5) The method of claim 5, wherein the coordinates of the centers of the fixed-size rectangular features include coordinates in a Cartesian coordinate system, wherein a first designated set of entries of the coordinate array provide x-coordinates of the centers of the fixed-size rectangular features, and wherein a second designated set of entries of the coordinate array provide y-coordinates of the centers of the fixed-size rectangular features. ### Claim 7 (depends on 1) The method of claim 1, further comprising applying post-processing to the generated synthetic coordinate arrays using a design rule check. ### Claim 8 (depends on 1) The method of claim 1, further comprising converting the generated synthetic coordinate arrays to a format used in an electronic design automation (EDA) software. ### Claim 9 (depends on 1) The method of claim 1, further comprising utilizing the synthetic coordinate array to evaluate manufacturability of the new physical design layout pattern. ### Claim 10 (depends on 1) The method of claim 1, further comprising displaying a visual representation of the generated synthetic coordinate arrays on a user interface. ### Claim 11 A non-transitory computer-readable storage medium comprising a computer-readable program for generating a plurality of physical design layout patterns, wherein the computer-readable program when executed on a computer causes the computer to perform the steps of: selecting one or more physical design layouts for neural network training; converting the plurality of physical design layout patterns into coordinate arrays, a coordinate array of the coordinate arrays including via center coordinates of vias in a physical design layout pattern of the plurality of physical design layout patterns; training, by employing the coordinate arrays, a variational autoencoder (VAE); and generating one or more new synthetic coordinate arrays by employing the trained VAE, a synthetic coordinate array of the one or more new synthetic coordinate arrays including via center coordinates of vias for a new physical design layout pattern. ### Claim 12 (depends on 11) The non-transitory computer-readable storage medium of claim 11, wherein the coordinate array has a size of M*N, where M is a number of values for representing center coordinates of respective ones of features in a designated coordinate system and N is a maximum number of vias in a field of view of the physical design layout pattern represented by the physical design layout pattern. ### Claim 13 (depends on 12) The non-transitory computer-readable storage medium of claim 12, wherein, when the field of view includes fewer than N vias, the coordinate array is padded with null values outside a range of possible coordinates for the field of view of the physical design layout pattern. ### Claim 14 (depends on 11) The non-transitory computer-readable storage medium of claim 11, wherein the vias of the one or more new synthetic coordinate arrays include fixed-size rectangular features. ### Claim 15 (depends on 14) The non-transitory computer-readable storage medium of claim 14, wherein the coordinate array includes designated entries for coordinates of respective ones of the centers of the fixed-size rectangular features. ### Claim 16 (depends on 15) The non-transitory computer-readable storage medium of claim 15, wherein the coordinates of the centers of the fixed-size rectangular features include coordinates in a Cartesian coordinate system, wherein a first designated set of entries of the coordinate array provide x-coordinates of the centers of the fixed-size rectangular features, and wherein a second designated set of entries of the coordinate array provide y-coordinates of the centers of the fixed-size rectangular features. ### Claim 17 (depends on 11) The non-transitory computer-readable storage medium of claim 11, wherein post-processing is applied to the generated synthetic coordinate arrays using a design rule check. ### Claim 18 (depends on 11) The non-transitory computer-readable storage medium of claim 11, wherein the generated synthetic coordinate arrays are converted to a format used in an electronic design automation (EDA) software. ### Claim 19 A system configured to train a machine learning based model, the system comprising: one or more computer subsystems; and one or more components executed by the one or more computer subsystems, wherein the one or more components include the machine learning based model configured for generating a plurality of physical design layout patterns by: selecting one or more physical design layouts for neural network training; converting the plurality of physical design layout patterns into coordinate arrays, a coordinate array of the coordinate arrays including via center coordinates of vias in a physical design layout pattern of the plurality of physical design layout patterns; training, by employing the coordinate arrays, a variational autoencoder (VAE); and generating one or more new synthetic coordinate arrays by employing the trained VAE, a synthetic coordinate array of the one or more new synthetic coordinate arrays including via center coordinates of vias for a new physical design layout pattern. ### Claim 20 (depends on 19) The system of claim 19, wherein the coordinate array has a size of M*N, where M is a number of values for representing center coordinates of respective ones of features in a designated coordinate system and N is a maximum number of vias in a field of view of the physical design layout pattern represented by the physical design layout pattern; and wherein, when the field of view includes fewer than N vias, the coordinate array is padded with null values outside a range of possible coordinates for the field of view of the physical design layout pattern.