International Business Machines Corporation

Rakuten Group, Inc.

Soinn Holdings LLC

Soinn Inc.

Daiki Kimura

Subhajit Chaudhury

Ryuki Tachibana

Asim Munawar

Michiaki Tatsubori

Gakuto Kurata

Osamu Hasegawa

Tadanobu Inoue

Masaki Ono

Ryosuke Kohita

Akifumi Wachi

Jason Marc Plawinski

Tristan Matthieu Stampfler

Next state prediction technology that performs the following computer based operations: receiving state information that includes information indicative of a current state of an environment; processing the state information to predict a future state of the environment, with the processing being performed by a hybrid computer system that includes both of the following: (i) neural network software module(s) that include machine learning functionality, and (ii) symbolic rule based software modules; and using the prediction of the next state of the environment as an input with respect to taking a further action (for example, activating a hardware device or effecting a communication to a human or another device).

Neuro-symbolic next state prediction based on multiple potential causes

A computer-implemented method for reinforcement learning with Logical Neural Networks (LNNs) is provided including receiving a plurality of observation text sentences from a target environment, extracting one or more propositional logic values from the plurality of observation text sentences, finding a class for each propositional logic value by using external knowledge, converting each propositional logic value into a first-order logic by replacing a part in the propositional logic value with a variable word, the part indicating the class, selecting a LNN based on the class among LNNs prepared in advance for each class, each LNN receiving the one or more propositional logic values as a status input and outputting an action with a score indicating a degree of preference for taking the action, and performing a highest score action to the target environment to obtain a next state of the target environment and a reward for the highest score action.

Neuro-symbolic reinforcement learning with first-order logic

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.

Learning unpaired multimodal feature matching for semi-supervised learning

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.

Anomaly detection by ranking from algorithm

In an approach, a processor trains a model, via a reinforcement learning process, to produce a first action function for relating states of a natural language based response environment to actions applicable to the natural language based response environment. A processor retrains the model, via the reinforcement learning process, to produce a second action function, including iterations of: applying the first action function to a current state representation of the natural language based response environment to obtain a ground-truth action representation, emphasizing a word of the current state representation based on relevancy to the ground-truth action representation to obtain a modified state representation, applying a model to the modified state representation to obtain an untrained action representation, and submitting the untrained action representation to a natural language based response environment to obtain a subsequent state representation, where the subsequent state representation becomes the current state representation for a subsequent iteration.

Text-based response environment action selection

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.

Closed loop model-based action learning with model-free inverse reinforcement learning

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.

Accelerated object labeling using prior geometric knowledge

Edge-Loss-based image construction is enabled by a method including generating a reconstructed image from a first edge image with a generator, extracting a second edge image from the reconstructed image with an edge extractor, smoothing the first edge image and the second edge image, discriminating between the reconstructed image and an original image corresponding to the first edge image with a discriminator to obtain an adversarial loss, and training the generator by using an edge loss and the adversarial loss, the edge loss being calculated from the smoothed first edge image and the smoothed second edge image.

Image reconstruction based on edge loss

The apparatus includes an image data obtainer, a candidate region extractor, a candidate line extractor, an overlap degree determiner, and a clip image region extractor. The candidate region extractor extracts, as a candidate region, a region containing an object detectable from the image data. The candidate line extractor extracts, as a candidate line, a line that is at least either a line segment or an arc included in the image data. The overlap degree determiner determines whether the degree of overlap between a closed line forming the outline of the candidate region extracted and the candidate line extracted is greater than or equal to a preset predetermined first percentage value. If the overlap degree determiner determines that the degree of overlap is greater than or equal to the first percentage value, the clip image region extractorextracts the candidate region as a clip image.

Image processing apparatus, image processing method, and image processing program for clipping images included in a large image

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.

Region of interest weighted anomaly detection

A transfer source operation information acquisition unit acquires a plurality of pieces of action information about the transfer source robot; a transfer destination operation information acquisition unit acquires a plurality of pieces of first action information about the transfer destination robot; and a correction unit generates a plurality of pieces of second action information about the transfer destination robot by correcting action information about the transfer source robot by a prescribed update formula using the first action information about the transfer destination robot. The number of the pieces of the first action information about the transfer destination robot is smaller than the number of the pieces of the action information about the transfer source robot, and the number of the pieces of the second action information about the transfer destination robot is larger than the number of the pieces of the first action information about the transfer destination robot.

Growing community of inventors

Tokyo, Japan

Daiki Kimura