Abstract: Methods and systems for a reinforcement learning system. A spatial and temporal representation of an observed state of an environment is encoded. A previous state is estimated from a given state and a size of a reward is adjusted based on a difference between the estimated previous state and the previous state.

Abstract: Balancing an imbalanced dataset, by: Receiving a balancing policy and the imbalanced dataset. Performing initial adjustment of the imbalanced dataset to comply with the balancing policy, by: oversampling one or more underrepresented classes, and, if one or more of the classes are overrepresented, undersampling them. Operating a generative machine learning model to generate samples for the one or more underrepresented classes, based on the initially-adjusted dataset. Operating a machine learning classification model to label the generated samples with class labels corresponding to the one or more underrepresented classes. Selecting some of the generated samples which, according to the labeling, have a relatively high probability of preserving their class labels.

Abstract: A specification of a property required to be upheld by a computerized machine learning system is obtained. A training data set corresponding to the property and inputs and outputs of the system is built. The system is trained on the training data set. Activity of the system is monitored before, during, and after the training. Based on the monitoring, performance of the system is evaluated to determine whether the system, once trained on the training data set, upholds the property.

Abstract: An example system includes a processor to receive a data set. The processor can generate a data slice rule based on a data observation for a data point in the data set. The processor can generate an instance of data based on the generated data slice rule.

Abstract: Embodiments of the present systems and methods may provide techniques for augmenting textual data that may be used for textual classification tasks. Embodiments of such techniques may provide the capability to synthesize labeled data to improve text classification tasks. Embodiments may be specifically useful when only a small amount of data is available, and provide improved performance in such cases. For example, in an embodiment, a method implemented in a computer system may comprise a processor, memory accessible by the processor, and computer program instructions stored in the memory and executable by the processor, and the method may comprise fine-tuning a language model using a training dataset, synthesizing a plurality of samples using the fine-tuned language model, filtering the plurality of synthesized samples, and generating an augmented training dataset comprising the training dataset and the filtered plurality of synthesized sentences.

Abstract: Balancing an imbalanced dataset, by: Receiving a balancing policy and the imbalanced dataset. Performing initial adjustment of the imbalanced dataset to comply with the balancing policy, by: oversampling one or more underrepresented classes, and, if one or more of the classes are overrepresented, undersampling them. Operating a generative machine learning model to generate samples for the one or more underrepresented classes, based on the initially-adjusted dataset. Operating a machine learning classification model to label the generated samples with class labels corresponding to the one or more underrepresented classes. Selecting some of the generated samples which, according to the labeling, have a relatively high probability of preserving their class labels.

Abstract: A technique includes extracting data from a historical data store representing completed work items and associated features of the work items. The work items are associated with a lifecycle stage of an application. The technique includes training a regression model to estimate a time for completing a given work item based at least in part on the features.

Abstract: Embodiments of the present systems and methods may provide techniques for augmenting textual data that may be used for textual classification tasks. Embodiments of such techniques may provide the capability to synthesize labeled data to improve text classification tasks. Embodiments may be specifically useful when only a small amount of data is available, and provide improved performance in such cases. For example, in an embodiment, a method implemented in a computer system may comprise a processor, memory accessible by the processor, and computer program instructions stored in the memory and executable by the processor, and the method may comprise fine-tuning a language model using a training dataset, synthesizing a plurality of samples using the fine-tuned language model, filtering the plurality of synthesized samples, and generating an augmented training dataset comprising the training dataset and the filtered plurality of synthesized sentences.

Abstract: In some examples, a system for executing natural language processing techniques can include a processor to detect text comprising a word and a number. The processor can also embed, via a word embedding model, the word into a first vector of a vector space and embed the number by converting the number into a second vector of the vector space. Additionally, the processor can train a deep neural network to execute instructions based on the first embedded vector of the word and the second embedded vector of the number. Furthermore, the processor can process an instruction based on the trained deep neural network.

Abstract: A specification of a property required to be upheld by a computerized machine learning system is obtained. A training data set corresponding to the property and inputs and outputs of the system is built. The system is trained on the training data set. Activity of the system is monitored before, during, and after the training. Based on the monitoring, performance of the system is evaluated to determine whether the system, once trained on the training data set, upholds the property.

Abstract: Methods and systems for a reinforcement learning system. A spatial and temporal representation of an observed state of an environment is encoded. A previous state is estimated from a given state and a size of a reward is adjusted based on a difference between the estimated previous state and the previous state.

Abstract: A set of predicted binary quality indexes is created from a sample set of application lifecycle information and customer encountered defects (CED) for each module id and revision (rev) pair for each application. Normalized effort and quality related factors are extracted for each module id and rev pair of each application. A binary quality index is created based on a set of weighted CED ratings for each module id and rev pair of each application. A prediction model for the binary quality index is created by training a decision tree-based classifier with the sample set to create a set of prediction weights for each effort and quality factor. The set of prediction weights is applied to the effort and quality related factors to each module id and rev pair of an application under-development to create the set of predicted binary quality indexes.

Abstract: In some examples, a method may include accessing data records of completed work items associated with managing a lifecycle of a software application and extracting feature values from the data records of the completed work items for a selected set of features. The method may also include determining timing data of state transitions for the completed work items from the data records and generating a predictor through machine learning using the timing data and the extracted feature values as input samples. The generated predictor may provide a transition probability of a particular state transition for a work item with specific feature values. The method may further include using the predictor to determine an estimated timing of the particular state transition for the uncompleted work item.

Abstract: A technique includes extracting data from a historical data store representing completed work items and associated features of the work items. The work items are associated with a lifecycle stage of an application. The technique includes training a regression model to estimate a time for completing a given work item based at least in part on the features.

Abstract: In some examples, a method may include accessing data records of completed work items associated with managing a lifecycle of a software application and extracting feature values from the data records of the completed work items for a selected set of features. The method may also include determining timing data of state transitions for the completed work items from the data records and generating a predictor through machine learning using the timing data and the extracted feature values as input samples. The generated predictor may provide a transition probability of a particular state transition for a work item with specific feature values. The method may further include using the predictor to determine an estimated timing of the particular state transition for the uncompleted work item.

Abstract: A set of predicted binary quality indexes is created from a sample set of application lifecycle information and customer encountered defects (CED) for each module id and revision (rev) pair for each application. Normalized effort and quality related factors are extracted for each module id and rev pair of each application. A binary quality index is created based on a set of weighted CED ratings for each module id and rev pair of each application. A prediction model for the binary quality index is created by training a decision tree-based classifier with the sample set to create a set of prediction weights for each effort and quality factor. The set of prediction weights is applied to the effort and quality related factors to each module id and rev pair of an application under-development to create the set of predicted binary quality indexes.