Abstract: A method of machine learning algorithm selection may include obtaining a dataset that includes multiple data entries. In some embodiments, each of the data entries may include multiple features and one of the multiple features may be designated as a target variable. The method may further include selecting a subset of the data entries. In some embodiments, selecting the subset of the data entries may include binning the data entries into multiple data bins based on values in the target variable and selecting a subset of the binned data entries from each of the multiple data bins as the subset of the data entries. The method may further include constructing multiple machine learning models using the subset of the data entries and selecting one of the multiple machine learning models based on an evaluation of the multiple machine learning models.

Abstract: According to an aspect of an embodiment, operations may include receiving an ML project stored in an ML corpus database. The operations may further include mutating a first ML pipeline, of a set of first ML pipelines associated with the received ML project, to determine a set of second ML pipelines. The mutation of the first ML pipeline may correspond to a substitution of a first ML model associated with the first ML pipeline with a second ML model associated with one of the set of predefined ML pipelines. The operations may further include selecting one or more ML pipelines from the set of second ML pipelines based on a performance score associated with each of the determined set of ML pipelines. The operations may further include augmenting the ML corpus database to include the selected one or more ML pipelines and the set of first ML pipeline.

Abstract: According to an aspect of an embodiment, operations may include receiving an ML project including a data-frame and an ML pipeline including a plurality of code statements associated with a plurality of features corresponding to the ML project. The operations may further include determining one or more atomic steps corresponding to the ML pipeline to determine an atomized ML pipeline. The operations may further include instrumenting the atomized ML pipeline to determine an instrumented ML pipeline including one or more operations corresponding to the ML project. The operations may further include executing the instrumented ML pipeline to capture one or more data-frame snapshots based on each of the one or more operations. The operations may further include constructing a feature provenance graph (FPG). The operations may further include identifying one or more discarded features, from the plurality of features corresponding to the ML project, based on the constructed FPG.

Abstract: According to an aspect of an embodiment, operations may include selecting, from a training dataset, a first data point as a seed data point. The operations may further include generating a population of data points by application of a genetic model on the seed data point. The population of data points may include the seed data point and a plurality of transformed data points of the seed data point. The operations may further include determining a best-fit data point in the generated population of data points based on application of a fitness function on the generated population of data points. The operations may further include executing a training operation on the DNN based on the determined best-fit data point. The operations may further include obtaining a trained DNN for the first data point based on the training operation on the DNN based on the determined best-fit data point.

Abstract: Operations include obtaining a machine learning (ML) pipeline skeleton that indicates a set of first functional blocks to use to process a new dataset of a new ML project. Additionally, for each respective first functional block of the set of first functional blocks, the operations include obtaining existing code snippets from existing ML pipelines, each of the existing code snippets instantiating a second functional block of the existing ML pipelines and being a potential instantiation of the respective first functional block. The operations also include determining a respective adaptability, with respect to the new dataset, of each of the existing code snippets and selecting a particular existing code snippet for implementation of the respective first functional block based on the determined adaptabilities. Further, the operations include instantiating the pipeline skeleton based on the particular existing code snippets.

Abstract: Operations include obtaining a machine learning (ML) pipeline skeleton that indicates a set of first functional blocks to use to process a new dataset of a new ML project. The operations also include obtaining a relationship mapping that maps dataset features to respective functional blocks, the relationship mapping indicating correspondences between dataset features of existing datasets of existing ML projects and usage of second functional blocks of existing ML pipelines of the existing ML projects. The operations also include mapping the first functional blocks to respective portions of the new dataset based on the relationship mapping. In addition, the operations include instantiating the pipeline skeleton with respective code snippets that each correspond to a respective first functional block of the set of first functional blocks, the respective code snippets each including one or more respective code elements that are based on the mapping of the first functional blocks.

Abstract: According to an aspect of an embodiment, operations may include selecting, from a training dataset, a first data point as a seed data point. The operations may further include generating a population of data points by application of a genetic model on the seed data point. The population of data points may include the seed data point and a plurality of transformed data points of the seed data point. The operations may further include determining a best-fit data point in the generated population of data points based on application of a fitness function on the generated population of data points. The operations may further include executing a training operation on the DNN based on the determined best-fit data point. The operations may further include obtaining a trained DNN for the first data point based on the training operation on the DNN based on the determined best-fit data point.

Abstract: According to an aspect of an embodiment, operations may include retrieving a set of repair patterns and a second set of violations of software programs. The operations may further include selecting an unfixed violation from the retrieved second set of violations and a repair pattern from the set of repair patterns. The operations may further include executing a first set of operations for refinement of repair patterns. The first set of operations may include applying the selected repair pattern on the selected unfixed violation, removing the applied repair pattern from the set of repair patterns based on the determination that a repair result corresponds to a violation. The first set of operations may further include reselecting next repair pattern as the selected repair pattern. The operations may further include obtaining a refined set of repair patterns by iteratively executing the first set of operations for the set of repair patterns.

Abstract: In one embodiment, a method includes accessing an event-driven application input by a user, the event-driven application comprising source code, one or more use cases input by the user for the event-driven application, and one or more functional requirements input by the user for the event-driven application; parsing the use cases and the functional requirements according to the predefined syntax to construct one or more validation modules for validating the event-driven application without any modification to the source code of the event-driven application for validation purposes; formally validating the event-driven application using the validation modules without relying on assertions inserted into the source code of the event-driven application for validation purposes; and if the formal validation finds one or more defects in the event-driven application, generating output for communication to the user identifying the defects.

Abstract: In one embodiment, a method includes accessing an event-driven application input by a user, the event-driven application comprising source code, one or more use cases input by the user for the event-driven application, and one or more functional requirements input by the user for the event-driven application; parsing the use cases and the functional requirements according to the predefined syntax to construct one or more validation modules for validating the event-driven application without any modification to the source code of the event-driven application for validation purposes; formally validating the event-driven application using the validation modules without relying on assertions inserted into the source code of the event-driven application for validation purposes; and if the formal validation finds one or more defects in the event-driven application, generating output for communication to the user identifying the defects.

Abstract: Estimating the difficulty level of a verification problem includes receiving input comprising a design and properties that may be verified on the design. Verification processes are performed for each property on the design. A property verifiability metric value is established for each property in accordance with the verification processes, where a property verifiability metric value represents a difficulty level of verifying the property on the design. A design verifiability metric value is determined from the property verifiability metric values, where the design verifiability metric value represents a difficulty level of verifying the design.

Abstract: A method for verifying a digital system design is provided. A first abstraction of a digital system design is performed to obtain an abstract model of the digital system design. One or more first steps of a multiple-step model checking process are performed using the abstract model, the multiple-step model checking process being operable to verify the digital system design. During the multiple-step model checking process, a second abstraction is performed to refine the abstract model. One or more second steps of the multiple-step model checking process are then performed using the refined abstract model.

Abstract: In one embodiment, a method for satisfiability (SAT)-based bounded model checking (BMC) includes isolating information learned from a first iteration of an SAT-based BMC process and applying the isolated information from the first iteration of the SAT-based BMC process to a second iteration of the SAT-based BMC process subsequent to the first iteration.

Abstract: In one embodiment, a method for scheduling events in a Boolean satisfiability (SAT) solver includes collecting one or more first-order statistics on a search for a valid solution to an SAT problem, deriving one or more second-order statistics on the search from the one or more first-order statistics, and scheduling events in the search according to one or more of the second-order statistics.