Abstract: At least one processor identifies dependency relationships among libraries in a repository of libraries. Using the dependency relationships among libraries, at least one machine learning model can be created that predicts with a confidence value a dependency between a given library and a target library. An L layer tree-like graph can be created, using the dependency relationships among libraries and an application package. L can be configurable. Versions of the libraries to use can be determined by running the at least one machine learning model for each pair of nodes having a dependency relationship in the L layer tree-like graph, the at least one machine learning model identifying the dependency relationship with a confidence value, where pairs of nodes having largest confidence values are selected as the versions of the libraries to use in the application package.

Abstract: Systems and techniques for determining an idle timeout for a cloud computing session are described. An example technique includes determining a first one or more attributes associated with a user of the cloud computing session and determining a second one or more attributes associated with an operation of the cloud computing session. An idle timeout for the cloud computing session is determined, based at least in part on the first one or more attributes and the second one or more attributes. User activity is monitored during the cloud computing session. Upon determining, based on the monitoring, an absence of the activity of the user within a duration of the idle timeout, the cloud computing session is terminated.

Abstract: Systems and techniques for determining an idle timeout for a cloud computing session are described. An example technique includes determining a first one or more attributes associated with a user of the cloud computing session and determining a second one or more attributes associated with an operation of the cloud computing session. An idle timeout for the cloud computing session is determined, based at least in part on the first one or more attributes and the second one or more attributes. User activity is monitored during the cloud computing session. Upon determining, based on the monitoring, an absence of the activity of the user within a duration of the idle timeout, the cloud computing session is terminated.

Abstract: Identifying node importance in a machine learning pipeline is provided. Changes in accuracy of the machine learning pipeline are recorded for each respective node setting change in a randomly generated group of node settings inputted into each corresponding node included in the machine learning pipeline. A regression model is generated to determine a relationship between each respective node setting change in the randomly generated group of node settings inputted into each corresponding node and the changes in the accuracy of the machine learning pipeline. A node of importance is identified in the machine learning pipeline using the regression model based on the relationship between each respective node setting change in the randomly generated group of node settings inputted into each corresponding node and the changes in the accuracy of the machine learning pipeline.

Abstract: An approach is provided in which the approach loads a machine learning model and a set of test case statistical data into a user system. The set of test case statistical data is based on a set of test cases corresponding to the machine learning model and includes a plurality of input parameter sets and a corresponding set of output quality measurements. The approach compares user data on the user system against the set of test case statistical data and identifies one of the plurality of input parameter sets to optimize the machine learning model based on the set of output quality measurements. The approach generates an optimized machine learning model using the machine learning model and the identified input parameter set at the user system.

Abstract: Embodiments of the present disclosure relate to screenshot-based memos. In an embodiment, a computer-implemented method is disclosed. The method comprises a monitoring displaying screen on a computing device for determining whether the displaying screen reaches a preset trigger condition. The method further comprises capturing a snapshot of the displaying screen in response to the displaying screen reaching the preset trigger condition. The method further comprises matching one or more screenshots comprised in one or more screenshot-based memos and the captured snapshot for obtaining a similarity degree. The method further comprises deploying the one or more screenshot-based memos on the displaying screen in response to the similarity degree meeting a preset similarity threshold. In other embodiments, a system and a computer program product are disclosed.