# US 10,504,040 B2 · Annealed sparsity via adaptive and dynamic shrinking > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,504,040 B2 - Document ID: US10504040B2 - Status: Granted - Kind: B2 - Application number: 15/160,280 - Filed: 2016-05-20 - Published: 2016-12-08 - Granted: 2019-12-10 - Earliest claimed: 2015-06-02 - Assignees: NEC Corporation - Applicants: NEC Laboratories America, Inc. - Inventors: Kai Zhang; Zhengzhang Chen; Haifeng Chen; Guofei Jiang - Web page: https://patentgrep.com/patent/US10504040B2 ## CPC - G06N 20/00: Machine learning - G16B 40/20: Supervised data analysis - G16H 30/20: for handling medical images, e.g. DICOM, HL7 or PACS - G16H 50/50: for simulation or modelling of medical disorders - G16H 40/63: for local operation - G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G16B: BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY - G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA ## Abstract Systems and methods are provided for acquiring data from an input signal using multitask regression. The method includes: receiving the input signal, the input signal including data that includes a plurality of features; determining at least two computational tasks to analyze within the input signal; regularizing all of the at least two tasks using shared adaptive weights; performing a multitask regression on the input signal to create a solution path for all of the at least two tasks, wherein the multitask regression includes updating a model coefficient and a regularization weight together under an equality norm constraint until convergence is reached, and updating the model coefficient and regularization weight together under an updated equality norm constraint that has a greater l1-penalty than the previous equality norm constraint until convergence is reached; selecting a sparse model from the solution path; constructing an image using the sparse model; and displaying the image. ## Claims ### Claim 1 A method for acquiring data from an input signal using multitask regression, comprising: receiving, into a memory, the input signal, the input signal including data that includes a plurality of features; determining at least two computational tasks to analyze within the input signal; regularizing all of the at least two tasks using shared adaptive weights; performing, using a processor, a multitask regression on the input signal to create a solution path for all of the at least two tasks, wherein the multitask regression includes: concurrently updating a model coefficient and a regularization weight together under an equality norm constraint until convergence is reached to produce a sparse model in the solution path; concurrently updating the model coefficient and regularization weight together under an updated equality norm constraint that has a greater l1-penalty than the previous equality norm constraint until convergence is reached to produce another sparse model in the solution path; and gradually strengthening a global magnitude of the l1-penalty by adjusting the equality norm constraint on the regularization weight by annealing to improve the convergence and reduce a sensitivity on initial conditions, wherein the shared adaptive weights w=[w1, w2, . . . , wD]T are used for the regularizing over all K tasks, as min w , B ⁢ ∑ K k = 1 ⁢ (  X k ⁢ β k - y k  2 2 +  w - γ ⊙ β k  ) , s.t. Σdwd=ω, wd≥0, wherein βk∈D×1 represents the model coefficient for a lth task for k=1, 2, . . . K, and B=[β1, β2, . . . , βk]; selecting a sparse model from the solution path; constructing an image using the sparse model; and displaying the image on a display. ### Claim 2 (depends on 1) The method as recited in claim 1, wherein the updating the model coefficient and the regularization weight further comprises: updating the model coefficient by training a Least Absolute Shrinkage and Selection Operator problem with a fixed regularization weight and solving the Least Absolute Shrinkage and Selection Operator problem for the model coefficient; and updating the regularization weight by training a constrained optimization problem with a fixed model coefficient and solving the constrained optimization problem for the regularization weight. ### Claim 3 (depends on 1) The method as recited in claim 1, further comprising recording the input signal, using a signal recorder, prior to receiving the input signal. ### Claim 4 (depends on 1) The method as recited in claim 1, wherein the performing the multitask regression increases a global regularization strength across the at least two tasks. ### Claim 5 (depends on 1) The method as recited in claim 1, wherein updating the equality norm constraint decreases a number of input signal features in the produced model. ### Claim 6 (depends on 5) The method as recited in claim 5, wherein the updating the model coefficient and regularization weight together under an updated equality norm constraint is repeated until a model is produced that is without features in the input signal. ### Claim 7 (depends on 1) The method as recited in claim 1, wherein the selecting a sparse model from the solution path further includes performing a cross-validation of all of the sparse models in the solution path. ### Claim 8 A system for acquiring data from an input signal using multitask regression, comprising: a memory to receive the input signal, the input signal including data that includes a plurality of features; a processor configured to: determine at least two computational tasks to analyze within the input signal; regularize all of the at least two tasks using shared adaptive weights; perform a multitask regression on the input signal to create a solution path for all of the at least two tasks, wherein the processor performs the multitask regression by: concurrently updating a model coefficient and a regularization weight together under an equality norm constraint until convergence is reached to produce a sparse model in the solution path; concurrently updating the model coefficient and regularization weight together under an updated equality norm constraint that has a greater l1-penalty than the previous equality norm constraint until convergence is reached to produce another sparse model in the solution path; and gradually strengthening a global magnitude of the l1-penalty by adjusting the equality norm constraint on the regularization weight by annealing to improve the convergence and reduce a sensitivity on initial conditions, wherein the shared adaptive weights w=[w1, w2, . . . , wD]T are used for the regularizing over all K tasks, as min w , B ⁢ ∑ K k = 1 ⁢ (  X k ⁢ β k - y k  2 2 +  w - γ ⊙ β k  ) , s.t. Σdwd=ω, wd≥0, wherein βk∈D×1 represents the model coefficient for a kth task for k=1, 2, . . . , K, and B=[β1, β2, . . . , βk]; select a sparse model from the solution path; and construct an image using the sparse model; and a display for displaying the constructed image. ### Claim 9 (depends on 8) The system as recited in claim 8, wherein the processor updates the model coefficient and the regularization weight together by: updating the model coefficient by training a Least Absolute Shrinkage and Selection Operator problem with a fixed regularization weight and solving the Least Absolute Shrinkage and Selection Operator problem for the model coefficient; and updating the regularization weight by training a constrained optimization problem with a fixed model coefficient and solving the constrained optimization problem for the regularization weight. ### Claim 10 (depends on 8) The system as recited in claim 8, further comprising a signal recorder for recording the input signal. ### Claim 11 (depends on 10) The system as recited in claim 10, wherein the processor, by performing the multitask regression, increases a global regularization strength across the at least two tasks. ### Claim 12 (depends on 8) The system as recited in claim 8, wherein updating the equality norm constraint decreases a number of input signal features in the produced model. ### Claim 13 (depends on 12) The system as recited in claim 12, wherein the processor is further configured to repeat the process of updating the model coefficient and regularization weight together under an updated equality norm constraint until a model is produced that is without features in the input signal. ### Claim 14 (depends on 8) The system as recited in claim 8, wherein the processor is further configured to perform a cross-validation of all of the sparse models in the solution path prior to selecting a sparse model from the solution path. ### Claim 15 A non-transitory computer-readable storage medium including a computer-readable program for assigning labels to an object, wherein the computer-readable program when executed on a computer causes the computer to perform the steps of: receiving, into a memory, the input signal, the input signal including data that includes a plurality of features; determining at least two computational tasks to analyze within the input signal; regularizing all of the at least two tasks using shared adaptive weights; performing, using a processor, a multitask regression on the input signal to create a solution path for all of the at least two tasks, wherein the multitask regression includes: updating a model coefficient and a regularization weight together under an equality norm constraint until convergence is reached to produce a sparse model in the solution path; updating the model coefficient and regularization weight together under an updated equality norm constraint that has a greater l1-penalty than the previous equality norm constraint until convergence is reached to produce another sparse model in the solution path; and gradually strengthening a global magnitude of the l1-penalty by adjusting the equality norm constraint on the regularization weight by annealing to improve the convergence and reduce a sensitivity on initial conditions, wherein the shared adaptive weights w=[w1, w2, . . . , wD]T are used for the regularizing over all K tasks, as min w , B ⁢ ∑ K k = 1 ⁢ (  X k ⁢ β k - y k  2 2 +  w - γ ⊙ β k  ) , s.t. Σdwd=ω, wd≥0, wherein βk∈D×1 represents the model coefficient for a kth task for k=1, 2, . . . , K, and B=[β1, β2, . . . , βk]; selecting a sparse model from the solution path; constructing an image using the sparse model; and displaying the image on a display. ### Claim 16 (depends on 15) The computer-readable storage medium as recited in claim 15, wherein the updating the model coefficient and the regularization weight further comprises: updating the model coefficient by training a Least Absolute Shrinkage and Selection Operator problem with a fixed regularization weight and solving the Least Absolute Shrinkage and Selection Operator problem for the model coefficient; and updating the regularization weight by training a constrained optimization problem with a fixed model coefficient and solving the constrained optimization problem for the regularization weight. ### Claim 17 (depends on 15) The computer-readable storage medium as recited in claim 15, further comprising recording the input signal, using a signal recorder, prior to receiving the input signal. ### Claim 18 (depends on 17) The computer-readable storage medium as recited in claim 17, wherein the performing the multitask regression increases a global regularization strength across the at least two tasks. ### Claim 19 (depends on 15) The computer-readable storage medium as recited in claim 15, wherein updating the equality norm constraint decreases a number of input signal features in the produced model. ### Claim 20 (depends on 19) The computer-readable storage medium as recited in claim 19, wherein the updating the model coefficient and regularization weight together under an updated equality norm constraint is repeated until a model is produced that is without features in the input signal.