Abstract: A computer-implemented method includes generating a single text data structure for a classifier of a speech recognition system, and sending the single text data structure to the classifier. Generating the single text data structure includes obtaining n-best hypotheses as an output of an automatic speech recognition (ASR) task for an utterance received by the speech recognition system, and combining the n-best hypotheses in a predetermined order with a separator between each pair of hypotheses to generate the single text data structure. The classifier is trained based on a single training text data structure by obtaining training source data, including selecting a first text sample and at least one similar text sample belong to a same class as the first text sample based on a maximum number of hypotheses, and arranging the plurality of text samples based on a degree of similarity.

Abstract: In an approach for propagating labels of objects in an image, a processor receives the image. A processor performs a normalization of the image. A processor runs the image through a pre-trained object detector. A processor receives a set of detected objects from the pre-trained object detector. A processor determines a width dimension and a height dimension of a bounding box for each detected object of the set of detected objects. A processor propagates a label for each instance of each detected object in the image with the respective bounding box using prior geometric knowledge of bounding box placement. A processor inverses the normalization of the labeled image. A processor outputs the labeled image.

Abstract: Anomalies are detected by generating a reconstructed dataset from an original dataset by using a generative model, calculating a differential dataset between the original dataset and the reconstructed dataset as a differential dataset, determining at least one of a region of interest of the original dataset and a region of interest of the reconstructed dataset, weighting the differential dataset by using the determined region of interest, and detecting an anomaly by using the weighted differential dataset.

Abstract: A computer-implemented method, computer program product, and system are provided for learning mapping information between different modalities of data. The method includes mapping, by a processor, high-dimensional modalities of data into a low-dimensional manifold to obtain therefor respective low-dimensional embeddings through at least a part of a first network. The method further includes projecting, by the processor, each of the respective low-dimensional embeddings to a common latent space to obtain therefor a respective one of separate latent space distributions in the common latent space through at least a part of a second network. The method also includes optimizing, by the processor, parameters of each of the networks by minimizing a distance between the separate latent space distributions in the common latent space using a variational lower bound. The method additionally includes outputting, by the processor, the parameters as the mapping information.

Abstract: A method for transferring acoustic knowledge of a trained acoustic model (AM) to a neural network (NN) includes reading, into memory, the NN and the AM, the AM being trained with target domain data, and a set of training data including a set of phoneme data, the set of training data being data obtained from a domain different from a target domain for the target domain data, inputting training data from the set of training data into the AM, calculating one or more posterior probabilities of context-dependent states corresponding to phonemes in a phoneme class of a phoneme to which each frame in the training data belongs, and generating a posterior probability vector from the one or more posterior probabilities, as a soft label for the NN, and inputting the training data into the NN and updating the NN, using the soft label.

Abstract: A computer-implemented method is provided for modified Lexicographic Reinforcement Learning. The computer implemented method includes obtaining, by a hardware processor, a sequence of tasks. Each of the tasks corresponds to, and has a one-to-one correspondence with, a respective award from among set of rewards. The method further includes performing, by the hardware processor for each of the tasks, reinforcement learning and deep learning for both of (i) one or more policies and (ii) one or more value functions, with a plurality of sets of samples. A plurality of solutions in a form of the one or more policies and the one or more value functions are parametrized by a single neural network with a selector which selects an input of the single neural network from among the plurality of sets of samples.

Abstract: A computer-implemented method executed by a robotic system for performing a positional search process in an assembly task is presented. The method includes decomposing, by the robotic system, a perturbation motion into a plurality of actions, the perturbation motion being a motion for an assembly position searched by the robotic system, each action of the plurality of actions related to a specific direction. The method further includes performing reinforcement learning by selecting an action among decomposed actions and assembly movement actions at each step of the positional search process based on corresponding force-torque data received from at least one sensor associated with the robotic system. The method also includes outputting a best action at each step for completion of the assembly task as a result of the reinforcement learning.

Abstract: Methods and systems for information retrieval include analyzing audio data to produce word hypotheses. Displaying the word hypotheses in motion at different respective speeds at once across a graphical display. Information is retrieved in accordance with one or more selected terms from the displayed word hypotheses.

Abstract: Methods and systems for information retrieval include analyzing audio data to produce one or more word hypotheses, each word hypothesis having an associated confidence value. The one or more word hypotheses are displayed in motion across a graphical display. Information retrieval is performed in accordance with one or more selected terms from the displayed word hypotheses.

Abstract: Anomalies are detected by generating a reconstructed dataset from an original dataset by using a generative model, calculating a differential dataset between the original dataset and the reconstructed dataset as a differential dataset, determining at least one of a region of interest of the original dataset and a region of interest of the reconstructed dataset, weighting the differential dataset by using the determined region of interest, and detecting an anomaly by using the weighted differential dataset.

Abstract: According to an aspect of the present invention, a computer-implemented method is provided for reinforcement learning. The method includes reading, by a processor device, an action manifold which is described as a n-polytope, at least one physical action limit, and at least one safety constraint. The method further includes updating, by the processor device, the action manifold based on the at least one physical action limit and the at least one safety constraint. The method also includes performing, by the processor device, the reinforcement learning by selecting a constrained action from among a set of constrained actions in the action manifold.

Abstract: A computer-implemented method, computer program product, and computer processing system are provided for obtaining a plurality of bad demonstrations. The method includes reading, by a processor device, a protagonist environment. The method further includes training, by the processor device, a plurality of antagonist agents to fail a task by reinforcement learning using the protagonist environment. The method also includes collecting, by the processor device, the plurality of bad demonstrations by playing the trained antagonist agents on the protagonist environment.

Abstract: A computer-implemented method, computer program product, and computer processing system are provided for Hierarchical Reinforcement Learning (HRL) with a target task. The method includes obtaining, by a processor device, a sequence of tasks based on hierarchical relations between the tasks, the tasks constituting the target task. The method further includes learning, by a processor device, a sequence of constraints corresponding to the sequence of tasks by repeating, for each of the tasks in the sequence, reinforcement learning and supervised learning with a set of good samples and a set of bad samples and by applying an obtained constraint for a current task to a next task.

Abstract: A method is provided for reinforcement learning. The method includes obtaining, by a processor device, a first set and a second set of state-action tuples. Each of the state-action tuples in the first set represents a respective good demonstration. Each of the state-action tuples in the second set represents a respective bad demonstration. The method further includes training, by the processor device using supervised learning with the first set and the second set, a neural network which takes as input a state to provide an output. The output is parameterized to obtain each of a plurality of real-valued constraint functions used for evaluation of each of a plurality of action constraints. The method also includes training, by the processor device, a policy using reinforcement learning by restricting actions predicted by the policy according to each of the plurality of action constraints with each of the plurality of real-valued constraint functions.

Abstract: A computer-implemented method for generating an input for a classifier. The method includes obtaining n-best hypotheses which is an output of an automatic speech recognition (ASR) for an utterance, combining the n-best hypotheses horizontally in a predetermined order with a separator between each pair of hypotheses, and outputting the combined n-best hypotheses as a single text input to a classifier.

Abstract: A computer-implemented method includes generating a single text data structure for a classifier of a speech recognition system, and sending the single text data structure to the classifier. Generating the single text data structure includes obtaining n-best hypotheses as an output of an automatic speech recognition (ASR) task for an utterance received by the speech recognition system, and combining the n-best hypotheses in a predetermined order with a separator between each pair of hypotheses to generate the single text data structure. The classifier is trained based on a single training text data structure by obtaining training source data, including selecting a first text sample and at least one similar text sample belong to a same class as the first text sample based on a maximum number of hypotheses, and arranging the plurality of text samples based on a degree of similarity.

Abstract: Symbol sequences are estimated using a computer-implemented method including detecting one or more candidates of a target symbol sequence from a speech-to-text data, extracting a related portion of each candidate from the speech-to-text data, detecting repetition of at least a partial sequence of each candidate within the related portion of the corresponding candidate, labeling the detected repetition with a repetition indication, and estimating whether each candidate is the target symbol sequence, using the corresponding related portion including the repetition indication of each of the candidates.

Abstract: Symbol sequences are estimated using a computer-implemented method including detecting one or more candidates of a target symbol sequence from a speech-to-text data, extracting a related portion of each candidate from the speech-to-text data, detecting repetition of at least a partial sequence of each candidate within the related portion of the corresponding candidate, labeling the detected repetition with a repetition indication, and estimating whether each candidate is the target symbol sequence, using the corresponding related portion including the repetition indication of each of the candidates.

Abstract: A computer-implemented method is provided for reinforcement learning performed by a processor. The method includes obtaining, from an environment, a given experience that includes an action, a state and a reward. The method further includes storing the given experience in an experience buffer responsive to a value of the reward included in the given experience exceeding a first threshold. The method also includes responsive to obtaining another experience having another reward that less than or equal to the first threshold, searching the experience buffer for a candidate experience with a similar state to the other experience and copying the candidate experience into an event buffer. The method additionally includes during exploration, selecting an action to be taken to the environment from the event buffer with a predetermined probability.

Abstract: A computer-implemented method is provided for learning an action policy. The method includes obtaining, by a processor, environment dynamics including triplets of a state, an action, and a next state. The state in each of the triplets is an expert state. The method further includes training, by the processor using the environment dynamics as training data, a dynamics model which obtains a pair of the state and the action as an input and outputs, for each next state, state-transition probabilities. The method also includes learning, by the processor, the action policy using trajectories of expert states according to a supervised learning technique by back-propagating error gradients through the trained dynamics model.