Abstract: A computer-implemented method of integrating an Artificial Intelligence (AI) planner and a reinforcement learning (RL) agent through AI planning annotation in RL (PaRL) includes identifying an RL problem. A description received of a Markov decision process (MDP) having a plurality of states in an RL environment is used to generate an RL task to solve the RL problem. An AI planning model described in a planning language is received, and mapping state spaces from the MDP states in the RL environment to AI planning states of the AI planning model is performed. The RL task is generated with an AI planning task from the mapping to generate a PaRL task.

Abstract: A method and a system for learning and applying neuro-symbolic multi-hop rules are provided. The method includes inputting training texts into a neural network as well as pre-defined entities. The training texts and the entities relate to a specific domain. The method also includes generating an entity graph made up of nodes and edges. The nodes represent the pre-defined entities, and the edges represent passages in the training texts with co-occurrence of the entities connected together by the edges. The method further includes determining a relation based on the passages for each of the pre-defined entities connected together by the edges, calculating a probability relating to the relation, generating a potential reasoning path between a head entity and a target entity. The method also includes learning a neuro-symbolic rule by converting the edges along the potential reasoning path into symbolic rules and combining those rules into the neuro-symbolic rule.

Abstract: A method and a system for learning and applying neuro-symbolic multi-hop rules are provided. The method includes inputting training texts into a neural network as well as pre-defined entities. The training texts and the entities relate to a specific domain. The method also includes generating an entity graph made up of nodes and edges. The nodes represent the pre-defined entities, and the edges represent passages in the training texts with co-occurrence of the entities connected together by the edges. The method further includes determining a relation based on the passages for each of the pre-defined entities connected together by the edges, calculating a probability relating to the relation, generating a potential reasoning path between a head entity and a target entity. The method also includes learning a neuro-symbolic rule by converting the edges along the potential reasoning path into symbolic rules and combining those rules into the neuro-symbolic rule.

Abstract: Techniques for learning from highly-diverse datasets are provided. In one embodiment, the system is provided that comprises a memory that stores computer executable components. The system can comprise a processor that executes the computer executable components stored in the memory. The computer executable components can comprise a neural network component that creates a neural network comprising a router that routes the neural network to a first layer of neurons that comprises a plurality of neurons. The computer executable components can comprise a training component that performs a plurality of successive training iterations on the neural network, a first iteration of the plurality of successive training iterations comprising both training the router to route among the plurality of neurons of the first layer of neurons, and training a first neuron of the plurality of neurons of the first layer of neurons to produce a given output from a given input.

Abstract: A system, method, and computer program product for automatically selecting from a plurality of analytic algorithms a best performing analytic algorithm to apply to a dataset is provided. The automatically selecting from the plurality of analytic algorithms the best performing analytic algorithm to apply to the dataset enables a training a plurality of analytic algorithms on a plurality of subsets of the dataset. Then, a corresponding prediction accuracy trend is estimated across the subsets for each of the plurality of analytic algorithms to produce a plurality of accuracy trends. Next, the best performing analytic algorithm is selected and outputted from the plurality of analytic algorithms based on the corresponding prediction accuracy trend with a highest value from the plurality of accuracy trends.

Abstract: A system, method, and computer program product for automatically selecting from a plurality of analytic algorithms a best performing analytic algorithm to apply to a dataset is provided. The automatically selecting from the plurality of analytic algorithms the best performing analytic algorithm to apply to the dataset enables a training a plurality of analytic algorithms on a plurality of subsets of the dataset. Then, a corresponding prediction accuracy trend is estimated across the subsets for each of the plurality of analytic algorithms to produce a plurality of accuracy trends. Next, the best performing analytic algorithm is selected and outputted from the plurality of analytic algorithms based on the corresponding prediction accuracy trend with a highest value from the plurality of accuracy trends.

Abstract: A graphical interface module may provide a set of graphical presentations comprising at least: a Likelihood of Delivery chart showing a probability distribution of predicted delivery dates; a Delivery Date Risk Trend chart showing how the completion time for the project predicted according to the Likelihood of Delivery chart has changed over time; and a Burndown chart that shows at least work-items of planned work for the project. Each of the Likelihood of Delivery chart, the Delivery Date Risk Trend chart, and the Burndown chart has a timeline axis.

Abstract: A system, method, and computer program product for automatically selecting from a plurality of analytic algorithms a best performing analytic algorithm to apply to a dataset is provided. The automatically selecting from the plurality of analytic algorithms the best performing analytic algorithm to apply to the dataset enables a training a plurality of analytic algorithms on a plurality of subsets of the dataset. Then, a corresponding prediction accuracy trend is estimated across the subsets for each of the plurality of analytic algorithms to produce a plurality of accuracy trends. Next, the best performing analytic algorithm is selected and outputted from the plurality of analytic algorithms based on the corresponding prediction accuracy trend with a highest value from the plurality of accuracy trends.

Abstract: Historic and current development data associated with the project may be gathered. A catalog of patterns, each pattern associated with a data measure and an analysis routine capable of detecting the pattern according to the data measure in a given data set may be obtained. A pattern describes a particular indication in the historical and development data, which arises one or more of, at a discrete point in time or over a period of time. The analysis routine may be applied to the historic and current development data. A notification may be issued responsive to identifying the pattern in the historic and current development data. The applying and the issuing may be performed for each pattern in the catalog of patterns.

Abstract: A system, method, and computer program product for automatically selecting from a plurality of analytic algorithms a best performing analytic algorithm to apply to a dataset is provided. The automatically selecting from the plurality of analytic algorithms the best performing analytic algorithm to apply to the dataset enables a training a plurality of analytic algorithms on a plurality of subsets of the dataset. Then, a corresponding prediction accuracy trend is estimated across the subsets for each of the plurality of analytic algorithms to produce a plurality of accuracy trends. Next, the best performing analytic algorithm is selected and outputted from the plurality of analytic algorithms based on the corresponding prediction accuracy trend with a highest value from the plurality of accuracy trends.

Abstract: Incorporating user insights in predicting, diagnosing and remediating problems that threaten on-time delivery of a project may comprise gathering information. The information may be conveyed to one or more users. A user may be allowed to input a new value associated with the project, the new value assessed based on the information and representing an expert assessment of the information. The user may be allowed to also indicate a period of time the user considers the information to be applicable. The new value and the period of time may be incorporated into data used in a prediction algorithm that predicts probability distribution of completion time of the project as the project is progressing.

Abstract: A user may be allowed to specify a change in one or more parameter data associated with the project, the one or more parameter data used previously to compute a probability distribution of completion time of the project. The probability distribution of completion time of the project may be recomputed based on the change. The recomputed probability distribution of the completion time of the project may be presented. An option to save the recomputed probability distribution may be provided. An option may be provided to specify another change in one or more parameter data associated with the project and repeat the recomputing and the presenting procedures based on another change in one or more parameter data associated with the project.

Abstract: A graphical interface module may provide a set of graphical presentations comprising at least: a Likelihood of Delivery chart showing a probability distribution of predicted delivery dates; a Delivery Date Risk Trend chart showing how the completion time for the project predicted according to the Likelihood of Delivery chart has changed over time; and a Burndown chart that shows at least work-items of planned work for the project. Each of the Likelihood of Delivery chart, the Delivery Date Risk Trend chart, and the Burndown chart has a timeline axis.

Abstract: A method (which can be computer implemented) for inferring whether at least a first relationship exists between at least first and second entities includes the steps of applying a first assessor to obtain a first confidence level pertaining to putative existence of said at least first relationship between said at least first and second entities, applying a second assessor to obtain a second confidence level pertaining to putative existence of said at least first relationship between said at least first and second entities, and combining said first and second confidence levels to obtain an overall inference whether said at least first relationship exists between said at least first and second entities.

Abstract: A graphical interface module may provide a set of graphical presentations comprising at least: a Likelihood of Delivery chart showing a probability distribution of predicted delivery dates; a Delivery Date Risk Trend chart showing how the completion time for the project predicted according to the Likelihood of Delivery chart has changed over time; and a Burndown chart that shows at least work-items of planned work for the project. Each of the Likelihood of Delivery chart, the Delivery Date Risk Trend chart, and the Burndown chart has a timeline axis.

Abstract: A task effort estimator may determine a probability distribution of an estimated effort needed to complete unfinished tasks in a project based on one or more of a set of completed tasks belonging to a project and attributes associated with the completed tasks belonging to the project, a set of completed tasks not belonging to the project and attributes associated with the completed tasks not belonging to the project, or the combination of both. A project completion predictor may determine a probability distribution of completion time for the project based on the probability distribution of an estimated effort needed to complete the unfinished tasks in the project, and one or more resource and scheduling constraints associated with the project.

Abstract: A method for projecting the progress of a project, the project including work items, the method including: obtaining starting state transition probabilities for the work items in a first time interval; obtaining starting populations of the work items, wherein the starting populations of the work items include states of the work items at the beginning of the first time interval; determining expected distributions for the work item states at the end of the first time interval by using the starting state transition probabilities and the starting populations; identifying actual states for the work items at the end of the first time interval; determining actual state transition rates of the work items for the first time interval by using the starting populations and the actual states; and determining expected future state transition probabilities for the work items by using the starting state transition probabilities and the actual state transition rates.

Abstract: A method (which can be computer implemented) for inferring whether at least a first relationship exists between at least first and second entities includes the steps of applying a first assessor to obtain a first confidence level pertaining to putative existence of said at least first relationship between said at least first and second entities, applying a second assessor to obtain a second confidence level pertaining to putative existence of said at least first relationship between said at least first and second entities, and combining said first and second confidence levels to obtain an overall inference whether said at least first relationship exists between said at least first and second entities.

Abstract: A method (which can be computer implemented) for inferring whether at least a first relationship exists between at least first and second entities includes the steps of applying a first assessor to obtain a first confidence level pertaining to putative existence of said at least first relationship between said at least first and second entities, applying a second assessor to obtain a second confidence level pertaining to putative existence of said at least first relationship between said at least first and second entities, and combining said first and second confidence levels to obtain an overall inference whether said at least first relationship exists between said at least first and second entities.

Abstract: A system and method to automatically and continuously update the urgency rating of a backlog item associated with a technical debt item in a software development project are described. The technical debt represents potential additional work or rework associated with current code. The method includes a user defining a plurality of components that comprise the software development project. The method also includes a processor associating the technical debt with one or more components of the plurality of components, and the processor updating the urgency of the backlog item associated with the technical debt according to a function based on a development event associated with at least one of the one or more components.