conferences

IBM Research at the Intersection of HCI and AI

IBM research on explainable AI, human-computer interaction (HCI), and automated ML featured at this year's conference on Intelligent User Interfaces.

Continue reading

Harnessing Dialogue for Interactive Career Goal Recommendations

An interactive career goal recommender framework that uses dialogue to incorporate user feedback and interactively improve the recommendations.

Continue reading

IBM Research AI at AAAI 2019

IBM Research AI will present dozens of technical papers and demos at the Thirty-Third AAAI Conference on Artificial Intelligence (AAAI) in Honolulu, Hawaii.

Continue reading

On-Line Learning of Linear Dynamical Systems with Kalman Filters

A forecasting method that is applicable to arbitrary sequences and comes with a regret bound competing against a class of methods, which includes Kalman filters.

Continue reading

Algebraic Gradient-Based Solver (AGS): A Novel Solver for Approximate Marginal MAP Inference

The Algebraic Gradient-based Solver (AGS), a novel solver for approximate marginal MAP inference, shows how ideas from planning can be used for inference.

Continue reading

IBM Research AI at 2018 Conference on Neural Information Processing Systems

At the Thirty-Second Conference on Neural Information Processing Systems in Montreal, IBM Research AI will share new ideas and results across our portfolio of research aimed at progressing AI towards real-world challenges. Throughout the week, we will present dozens of papers and demos showcasing our work, as listed below. In addition, we will highlight three […]

Continue reading

Graph2Seq: A Generalized Seq2Seq Model for Graph Inputs

In a recent paper “Graph2Seq: Graph to Sequence Learning with Attention-based Neural Networks,” we describe a general end-to-end Graph-to-Sequence attention-based neural encoder-decoder architecture that encodes an input graph and decodes the target sequence. Graph encoder and attention-based decoder are two important building blocks in the development and widespread acceptance of machine learning solutions. Two of […]

Continue reading

Word Mover’s Embedding: Universal Text Embedding from Word2Vec

Text representation plays an important role in many natural language processing (NLP) tasks such as document classification and clustering, sense disambiguation, machine translation, and document matching. Since there are no explicit features in text, developing effective text representations is an important goal in AI and NLP research. A fundamental challenge in this respect is learning […]

Continue reading

Sensemaker Series: IBM Researchers on Future Tech for Financial Services

The financial services industry faces mounting pressures to reduce costs, improve customer experience, compete with emerging players, and comply with new regulations. At the same time, IBM Research is driving innovations that will transform the financial services industries using technologies like AI, blockchain, quantum computing, IoT, cybersecurity, and cloud. These advances are surfacing new capabilities […]

Continue reading

Helping to Improve Medical Image Analysis with Deep Learning

Medical imaging creates tremendous amounts of data: many emergency room radiologists must examine as many as 200 cases each day, and some medical studies contain up to 3,000 images. Each patient’s image collection can contain 250GB of data, ultimately creating collections across organizations that are petabytes in size. Within IBM Research, we see potential in […]

Continue reading

Using AI to Design Deep Learning Architectures

Selecting the best architecture for deep learning architectures is typically a time-consuming process that requires expert input, but using AI can streamline this process. I am developing an evolutionary algorithm for architecture selection that is up to 50,000 times faster than other methods, with only a small increase in error rate. Deep learning models are […]

Continue reading

An End-to-End Approach for Scaling Up Spectral Clustering

Clustering is one of the most fundamental problems in machine learning and data mining tasks, such as image segmentation, power load clustering, and community detection for social networks. But well-known clustering techniques like K-Means, which is based on Euclidean proximity, may not be capable of clustering data that lies on a high-dimensional manifold, as illustrated […]

Continue reading