Abstract: One or more systems, devices, computer program products, and/or computer-implemented methods provided herein relate to accurate anomaly detection in images using patched features. According to an embodiment, an extraction component can extract multiple layers of features from one or more patches of an image using a pretrained convolutional neural network (CNN). A feature mapping component can concatenate the features from the multiple layers to generate a tensor feature map comprising a one-dimensional feature vector for respective patches. A cropping component can perform center cropping on the tensor feature map. A calculation component can calculate a distance to a feature distribution mean for respective patches.

Abstract: A computerized machine learning anomaly detection model trained on a plurality of samples of one or more source domains (optionally, one or more source domains and the target domain) is accessed. Using online deep sets, one or more domain vectors are computed for each target domain sample at an observation point, each target domain sample corresponding to a given target domain, where the one or more domain vectors represent a similarity and difference among the source and target domains. The target domain sample is processed using the anomaly detection model trained on the plurality of samples of the source to generate an anomaly score, the processing being based on the computed one or more domain vectors.

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: Embodiments of the invention describe a computer-implemented method of detecting anomalous data associated with a system-under-analysis. The computer-implemented method includes using a first encoder stage of a neural network to generate content-irrelevant latent code from input data. A second encoder stage of the neural network is used to generate domain-irrelevant latent code from the input data. A decoder stage of the neural network is used to generate reconstructed input data. The reconstructed input data includes a reconstruction of the input data based at least in part on the content-irrelevant latent code and the domain-irrelevant latent code. A reconstruction loss is generated based at least in part on the reconstructed input data. The reconstruction loss is used to determine that the input data includes an anomalous data candidate.

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: Aspects of the present invention disclose a method for a distance-based vector classification in anomaly detection. The method includes one or more processors identifying one or more audio communications from a first user to a second user, wherein the one or more audio communications is transmitted utilizing a first computing device. The method further includes determining an objective of the first user based at least in part on the audio communication of the first user. The method further includes determining a set of conditions corresponding to the one or more audio communications and the objective, wherein the set of conditions indicate a vulnerability of personal data of the first user. The method further includes prohibiting the first computing device from transmitting audio data that includes the personal data of the first user.

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: Methods and computer program products for training a neural network perform multiple forms of data augmentation on sample waveforms of a training dataset that includes both normal and abnormal samples to generate normal data augmentation samples and abnormal data augmentation samples. The normal data augmentation samples are labeled according to a type of data augmentation that was performed on each respective normal data augmentation sample. The abnormal data augmentation samples are labeled according to a type of data augmentation other than that which was performed on each respective abnormal data augmentation sample. A neural network model is trained to identify a form of data augmentation that has been performed on a waveform using the normal data augmentation samples and the abnormal data augmentation samples.

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 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.

Abstract: A computer-implemented method, computer program product, and system are provided for deep reinforcement learning to control a subject device. The method includes training, by a processor, a neural network to receive state information of a target of the subject device as an input and provide action information for the target as an output. The method further includes inputting, by the processor, current state information of the target into the neural network to obtain current action information for the target. The method also includes correcting, by the processor, the current action information minimally to obtain corrected action information that meets a set of constraints. The method additionally includes performing an action by the subject device based on the corrected action information for the target to obtain a reward from the target.

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, systems, and computer program products for detecting anomalous behavior include reconstructing a waveform of a target device from an input waveform using a target autoencoder. A waveform of unrelated sound events is reconstructed from the input waveform using an environmental autoencoder. The input waveform is classified to determine that the input waveform is produced by anomalous behavior of the target device using a classifier, based on the reconstructed waveform of the target device and the reconstructed waveform of the unrelated sound events. An automatic response to the anomalous behavior is generated.

Abstract: Methods, systems, and computer program products for detecting anomalous behavior include reconstructing a waveform of a target device from an input waveform using a target autoencoder. A waveform of unrelated sound events is reconstructed from the input waveform using an environmental autoencoder. The input waveform is classified to determine that the input waveform is produced by anomalous behavior of the target device using a classifier, based on the reconstructed waveform of the target device and the reconstructed waveform of the unrelated sound events. An automatic response to the anomalous behavior is generated.

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 is provided for learning multimodal feature matching. The method includes training an image encoder to obtain encoded images. The method further includes training a common classifier on the encoded images by using labeled images. The method also includes training a text encoder while keeping the common classifier in a fixed configuration by using learned text embeddings and corresponding labels for the learned text embeddings. The text encoder is further trained to match a distance of predicted text embeddings which is encoded by the text encoder to a fitted Gaussian distribution on the encoded images.

Abstract: Methods and systems for anomaly detection include training a neural network model to identify a form of data augmentation that has been performed on a waveform. Multiple forms of data augmentation are performed on a sample waveform to generate data augmentation samples. The data augmentation samples are classified with the neural network model. An anomaly score is determined based on the classification of the data augmentation samples.

Abstract: Aspects of the present invention disclose a method for a distance-based vector classification in anomaly detection. The method includes one or more processors identifying one or more audio communications from a first user to a second user, wherein the one or more audio communications is transmitted utilizing a first computing device. The method further includes determining an objective of the first user based at least in part on the audio communication of the first user. The method further includes determining a set of conditions corresponding to the one or more audio communications and the objective, wherein the set of conditions indicate a vulnerability of personal data of the first user. The method further includes prohibiting the first computing device from transmitting audio data that includes the personal data of the first user.

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: 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.