International Business Machines Corporation

Rensselaer Polytechnic Institute

Massachusetts Institute of Technology

Chuang Gan

Dakuo Wang

Yang Zhang

Bo Wu

Ming Tan

Sijia Liu

Mo Yu

Haoyu Wang

Pin-Yu Chen

Abel Nicolas Valente

Zhenfang Chen

Jing James Xu

Bei Chen

Ji Hui Yang

Shiyu Chang

Xiaoxiao Guo

Arunima Chaudhary

Daniel Karl I Weidele

Kaizhi Qian

Qi Cheng Li

Si Er Han

Gaoyuan Zhang

Quanfu Fan

Lingfei Wu

Jun Song Wang

Horst Cornelius Samulowitz

Dhavalkumar C Patel

Long H Vu

Syed Yousaf Shah

Gregory Bramble

Rameswar Panda

Qian Pan

Yi Wang

Abhishek Bhandwaldar

Yupeng Gao

Xuye Liu

Ao Liu

Lirong Xia

Xin Ru Wang

Xin Zhou

Jinjun Xiong

Xin Zhang

Anbang Xu

Xue Ying Zhang

Lisa Amini

Saloni Potdar

Peter Daniel Kirchner

Jun Wang

Yufang Hou

Lijun Mei

David A Cox

Yunfeng Zhang

Tengfei Ma

David E Cox

Xiaotong Liu

Saket Sathe

Murray Scott Campbell

Antonio Jose Jimeno Yepes

Haibin Liu

Xuan-Hong Dang

Udayan Khurana

Subhro Das

Lin Ju

Jason Tsay

Tejaswini Pedapati

John Dillon Eversman

Voranouth Supadulya

Hao Ac Chen

Akhilan Boopathy

Shun Zhang

Shaoze Fan

Chunheng Jiang

Jianxi Gao

Cheng-I Lai

Alexander Haojan Liu

Carolina Maria Spina

Songtao Lu

Dongyu Liu

Yi Sun

James R Glass

Edward Sun

A computerized method, system and computer program product for building a dialogue flow. One embodiment of the method may comprise receiving an input document, the input document comprising content, and generating, by a question-answer pipeline, a plurality of question-answer pairs from the content of the input document. For each question-answer pair, the method may further comprise feeding the question of the question-answer pair into an intent of a dialogue flow structure, and feeding the answer of the question-answer pair as one response of the intent. The method may further comprise tagging each of the plurality of question-answer pairs with a corresponding document section index, reading, by a conversational agent, the input document to a user, pausing the reading when the conversational agent reaches one of the document section indices in the input document, and in response, reading the question corresponding to the document section indicia to the user.

Automated generation of dialogue flow from documents

Scalable distributed adversarial training techniques for robust deep neural networks are provided. In one aspect, a method for adversarial training of a deep neural network-based model by distributed computing machines M includes, by distributed computing machines M: obtaining adversarial perturbation-modified training examples for samples in a local dataset D; computing gradients of a local cost function ƒwith respect to parameters θ of the deep neural network-based model using the adversarial perturbation-modified training examples; transmitting the gradients of the local cost function ƒto a server which aggregates the gradients of the local cost function ƒand transmits an aggregated gradient to the distributed computing machines M; and updating the parameters θ of the deep neural network-based model stored at each of the distributed computing machines M based on the aggregated gradient received from the server. A method for distributed adversarial training of a deep neural network-based model by the server is also provided.

Distributed adversarial training for robust deep neural networks

An output layer is removed from a pre-trained neural network model and a neural capacitance probe unit with multiple layers is incorporated on top of one or more bottom layers of the pre-trained neural network model. The neural capacitance probe unit is randomly initialized and a modified neural network model is trained by fine-tuning the one or more bottom layers on a target dataset for a maximum number of epochs, the modified neural network model comprising the neural capacitance probe unit incorporated with multiple layers on top of the one or more bottom layers of the pre-trained neural network model. An adjacency matrix is obtained from the initialized neural capacitance probe unit and a neural capacitance metric is computed using the adjacency matrix. An active model is selected using the neural capacitance metric and a machine learning system is configured using the active model.

Neural capacitance: neural network selection via edge dynamics

A dataset including features and values associated with the features can be received. Each of the features in the dataset can be mapped to a corresponding node in a knowledge graph based on the concept represented by the corresponding node. The knowledge graph can be traversed to find a candidate node connected to at least one mapped node, the candidate node not being mapped to a feature in the dataset. A concept associated with the candidate node can be identified as a new feature. A machine learning model pipeline can use the features in the dataset and the new feature to select a subset of features for training a machine learning model.

Interactive feature engineering in automatic machine learning with domain knowledge

A system may include a memory and a processor in communication with the memory. The processor may be configured to perform operations. The operations may include receiving an input, extracting features from the input, and mining object relations using the features. The operations may include determining feature vectors using the object relations and generating, using the feature vectors, an output indicating a target region, wherein the target region corresponds to the input.

Image grounding with modularized graph attentive networks

According to one embodiment, a method, computer system, and computer program product for identifying one or more intrinsic physical properties of one or more objects is provided. The present invention may include identifying one or more objects in a video set, extracting observable physical properties of the identified one or more objects from the video set, including one or more trajectories, and inferring, by a property-based graph neural network, intrinsic properties of the one or more objects based on the trajectories.

Object-centric and relation-centric graph neural networks for physical property discovery

One or more computer processors obtain an initial subnetwork at a target sparsity and an initial pruning mask from a pre-trained self-supervised learning (SSL) speech model. The one or more computer processors finetune the initial subnetwork, comprising: the one or more computer processors zero out one or more masked weights in the initial subnetwork specified by the initial pruning mask; the one or more computer processors train a new subnetwork from the zeroed out subnetwork; the one or more computer processors prune one or more weights of lowest magnitude in the new subnetwork regardless of network structure to satisfy the target sparsity. The one or more computer processors classify an audio segment with the finetuned subnetwork.

Self-supervised speech recognition

Use a computerized trained graph neural network model to classify an input instance with a predicted label. With a computerized graph neural network interpretation module, compute a gradient-based saliency matrix based on the input instance and the predicted label, by taking a partial derivative of class prediction with respect to an adjacency matrix of the model. With a computerized user interface, obtain user input responsive to the gradient-based saliency matrix. Optionally, modify the trained graph neural network model based on the user input; and re-classify the input instance with a new predicted label based on the modified trained graph neural network model.

Interpretable visualization system for graph neural network

Mechanisms are provided for performing artificial intelligence-based video question answering. A video parser parses an input video data sequence to generate situation data structure(s), each situation data structure comprising data elements corresponding to entities, and first relationships between entities, identified by the video parser as present in images of the input video data sequence. First machine learning computer model(s) operate on the situation data structure(s) to predict second relationship(s) between the situation data structure(s). Second machine learning computer model(s) execute on a received input question to predict an executable program to execute to answer the received question. The program is executed on the situation data structure(s) and predicted second relationship(s). An answer to the question is output based on results of executing the program.

Neural-symbolic action transformers for video question answering

A vehicle light signal detection and recognition method, system, and computer program product include bounding, using a coarse attention module, one or more regions of an image of an automobile including at least one of a brake light and a signal light generated by automobile signals which include illuminated sections to generate one or more bounded region, removing, using a fine attention module, noise from the one or more bounded regions to generate one or more noise-free bounded regions, and identifying the at least one of the brake light and the signal light from the one or more noise-free bounded regions.

Coarse-to-fine attention networks for light signal detection and recognition

A method (and structure and computer product) for an audiovisual source separation processing, including receiving video data including images of a plurality of sound sources, receiving an optical flow data of the video data, the optical flow data indicating motions of pixels between frames of the video data, and encoding the received video data into video localization data comprising information associating pixels in the frames of video data with different channels of sound.

Audiovisual source separation and localization using generative adversarial networks

A processor may receive a video including a plurality of video frames in sequence and a question regarding the video. For a video frame in the plurality of video frames, a processor may parse the video frame into objects and relationships between the objects, and create a subgraph of nodes representing objects and edges representing the relationships, where parsing and creating are performed for each video frame in the plurality of video frames, where a plurality of subgraphs can be created. A processor may create a hypergraph connecting subgraphs by learning relationships between the nodes of the subgraphs, where a hyper-edge is created to represent a relationship between at least one node of one subgraph and at least one node of another subgraph in the plurality of subgraphs. A processor may generate an answer to the question based on the hypergraph.

Transformers for real world video question answering

Techniques regarding transferring learning outcomes across machine learning tasks in automated machine learning systems are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise a transfer learning component that can executes a machine learning task using an existing artificial intelligence model on a sample dataset based on a similarity between the sample dataset and a historical dataset. The existing artificial intelligence model can be generated by automated machine learning and trained on the historical dataset.

Transfer learning across automated machine learning systems

One or more computer processors improve action recognition by removing inference introduced by visual appearances of objects within a received video segment. The one or more computer processors extract appearance information and structure information from a received video segment. The one or more computer processors calculate a factual inference (TE) for the received video segment utilizing the extracted appearance information and structure information. The one or more computer processors calculate a counterfactual debiasing inference (NDE) for the received video segment. The one or more computer processors calculate a total indirect effect (TIE) by subtracting the calculated counterfactual debiased inference from the calculated factual inference. The one or more computer processors action recognize the received video segment by selecting a classification result associated with a highest calculated TIE.

Counterfactual debiasing inference for compositional action recognition

Mechanisms are provided for implementing a generative adversarial network (GAN) based restoration system. A first neural network of a generator of the GAN based restoration system is trained to generate an artificial audio spectrogram having a target damage characteristic based on an input audio spectrogram and a target damage vector. An original audio recording spectrogram is input to the trained generator, where the original audio recording spectrogram corresponds to an original audio recording and an input target damage vector. The trained generator processes the original audio recording spectrogram to generate an artificial audio recording spectrogram having a level of damage corresponding to the input target damage vector. A spectrogram inversion module converts the artificial audio recording spectrogram to an artificial audio recording waveform output.

Generative adversarial network based audio restoration

Growing community of inventors

Cambridge, MA, United States of America

Chuang Gan