# US 11,308,395 B2 · Method and system for performing machine learning > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,308,395 B2 - Document ID: US11308395B2 - Status: Granted - Kind: B2 - Application number: 16/396,563 - Filed: 2019-04-26 - Published: 2019-10-31 - Granted: 2022-04-19 - Earliest claimed: 2018-04-27 - Assignees: Alibaba Group Holding Limited - Applicants: Alibaba Group Holding Limited - Inventors: Liang Han - Web page: https://patentgrep.com/patent/US11308395B2 ## CPC - G06N 3/045: Combinations of networks - G06N 3/082: modifying the architecture, e.g. adding, deleting or silencing nodes or connections - G06N 3/044: Recurrent networks, e.g. Hopfield networks - G06N 3/0442: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU] - G06N 3/0464: Convolutional networks [CNN, ConvNet] - G06N 3/048: Activation functions - G06N 3/0495: Quantised networks; Sparse networks; Compressed networks - G06N 3/09: Supervised learning - G06N 20/00: Machine learning - G06N 3/063: using electronic means - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract Embodiments of the disclosure provide methods and systems for performing machine learning. The method can include: receiving training data; training a machine learning model based on the training data, wherein the machine learning model includes multiple layers each having one or more nodes having one or more connections with a node from another layer of the machine learning model; evaluating weights associated with the connections of the machine learning model, wherein each connection has a corresponding weight; removing, from the machine learning model, one or more connections having a weight that does not satisfy a threshold condition; and after the connections have been removed, updating the machine learning model. ## Claims ### Claim 1 A computer-implemented method comprising: receiving training data; training a machine learning model based on the training data, wherein the machine learning model includes multiple layers each having one or more nodes having one or more connections with a node from another layer of the machine learning model; evaluating weights associated with the connections of the machine learning model, wherein each connection has a corresponding weight; removing, from the machine learning model, one or more connections having a weight that does not satisfy a threshold condition; evaluating layer weights associated with the layers of the machine learning model, wherein each layer has a corresponding layer weight; removing, from the machine learning model, one or more layers having a layer weight that does not satisfy a layer threshold condition; and after the connections and the one or more layers have been removed, updating the machine learning model. ### Claim 2 (depends on 1) The method according to claim 1, wherein receiving the training data further comprises: reducing the training data by removing a portion of the training data. ### Claim 3 (depends on 2) The method according to claim 2, wherein the training data includes a plurality of dimensions, and the removed portion is associated with at least one dimension. ### Claim 4 (depends on 2) The method according to claim 2, wherein the training data includes first data associated with a first moment and second data associated with a second moment, and reducing the training data by removing the portion of the training data further comprises: removing the first data associated with the first moment from the training data. ### Claim 5 (depends on 1) The method according to claim 1, further comprising: generating a filter for evaluating input data to be provided to the machine learning model. ### Claim 6 A non-transitory computer readable medium that stores a set of instructions that is executable by at least one processor of a computer system to cause the computer system to perform a method for simplifying a machine learning model, the method comprising: receiving training data; training a machine learning model based on the training data, wherein the machine learning model includes multiple layers each having one or more nodes having one or more connections with a node from another layer of the machine learning model; evaluating weights associated with the connections of the machine learning model, wherein each connection has a corresponding weight; removing, from the machine learning model, one or more connections having a weight that does not satisfy a threshold condition; evaluating layer weights associated with the layers of the machine learning model, wherein each layer has a corresponding layer weight; removing, from the machine learning model, one or more layers having a layer weight that does not satisfy a layer threshold condition; and after the connections and the one or more layers have been removed, updating the machine learning model. ### Claim 7 (depends on 6) The non-transitory computer readable medium according to claim 6, wherein receiving the training data further comprises: reducing the training data by removing a portion of the training data. ### Claim 8 (depends on 6) The non-transitory computer readable medium according to claim 6, wherein the training data includes a plurality of dimensions, and the removed portion is associated with at least one dimension. ### Claim 9 (depends on 7) The non-transitory computer readable medium according to claim 7, wherein the training data includes first data associated with a first moment and second data associated with a second moment, and reducing the training data by removing the portion of the training data further comprises: removing the first data associated with the first moment from the training data. ### Claim 10 (depends on 6) The non-transitory computer readable medium according to claim 6, wherein the set of instructions is further executed by the at least one processor of the computer system to cause the computer system to perform: generating a filter for evaluating input data to be provided to the machine learning model. ### Claim 11 A computer system, comprising: a memory storing a set of instructions; and at least one processor configured to execute the set of instructions to cause the system to perform: receiving training data; training a machine learning model based on the training data, wherein the machine learning model includes multiple layers each having one or more nodes having one or more connections with a node from another layer of the machine learning model; evaluating weights associated with the connections of the machine learning model, wherein each connection has a corresponding weight; removing, from the machine learning model, one or more connections having a weight that does not satisfy a threshold condition; evaluating layer weights associated with the layers of the machine learning model, wherein each layer has a corresponding layer weight; removing, from the machine learning model, one or more layers having a layer weight that does not satisfy a layer threshold condition; and after the connections and the one or more layers have been removed, updating the machine learning model. ### Claim 12 (depends on 5) The method according to claim 5, further comprising: processing the input data to comprise guiding information using the filter, and the processed input data is configured to bypass at least one connection of the machine learning model based on the guiding information.