AI

IBM Research AI: Advancing AI for industry and society

Pushing the boundaries of convex optimization

Convex optimization problems, which involve the minimization of a convex function over a convex set, can be approximated in theory to any fixed precision in polynomial time. However, practical algorithms are known only for special cases. An important question is whether it is possible to develop algorithms for a broader subset of convex optimization problems that are efficient in both theory and practice.

Continue reading

Making Neural Networks Robust with New Perspectives

IBM researchers have partnered with scientists from MIT, Northeastern University, Boston University and University of Minnesota to publish two papers on novel attacks and defenses for graph neural networks and on a new robust training algorithm called hierarchical random switching at IJCAI 2019.

Continue reading

Improving the Scalability of AI Planning when Memory is Limited

We report new research results relevant to AI planning in our paper, "Depth-First Memory-Limited AND/OR Search and Unsolvability in Cyclic Search Spaces," presented at the International Joint Conference on Artificial Intelligence, IJCAI-19.

Continue reading

Causal Knowledge Extraction: An Evaluation using Automated Binary Causal Question Answering

At IJCAI'19, IBM researchers present new results on causal knowledge extraction from large amounts of text for applications in enterprise risk management.

Continue reading

IBM Research AI @ IJCAI 2019

At IJCAI-19, IBM Research AI will present technical papers exploring a variety of topics in AI including neurosymbolic reasoning, explainability, adversarial robustness, computational linguistics, graph analysis, optimization, and reinforcement learning.

Continue reading

Introducing AI Explainability 360

IBM Research AI announced AI Explainability 360, a comprehensive open-source toolkit of state-of-the-art algorithms that support the interpretability and explainability of machine learning models.

Continue reading

Answering Complex Questions using Neural Program Induction

At ACL 2019, IBM researchers released a paper detailing the model they trained to answer complex questions using Neural Program Induction, which allows an AI model can be taught to procedurally decompose a complex task into a program.

Continue reading

Adversarial Learning and Zeroth Order Optimization for Machine Learning and Data Mining

There is a growing number of adversarial attacks and nefarious behaviors aimed at AI systems. To combat this, IBM Research AI will present multiple papers that yield new scientific discoveries and recommendations related to adversarial learning at KDD 2019.

Continue reading

IBM Research AI at KDD 2019

At KDD 2019, IBM Research AI will present technical papers describing the latest results in deep learning for graphs, adversarial learning, text understanding, and data science for healthcare, financial crimes, and scientific discovery.

Continue reading

Help build the next generation of AI-driven dialog systems

IBM Research AI and the University of Michigan are organizing a public competition to inspire and evaluate novel approaches that will lead to the next generation of AI-driven dialog systems.

Continue reading

Overcoming Challenges in Building Enterprise AI Assistants

A team of researchers from IBM Research AI and AI Horizons Network-partner the University of Michigan published the papers “A Large-Scale Corpus for Conversation Disentanglement” and “Learning End-to-End Goal-Oriented Dialog with Maximal User Task Success and Minimal Human Agent Use” at ACL 2019. This work address two main challenges in building enterprise AI assistants.

Continue reading

With HEIDL, Humans and Machines Can Work Together to Cut Through Legalese

At ACL 2019, IBM researchers will present a demonstration of HEIDL, a model that makes it easier and much faster for people to review the effectiveness of natural language labels generated by a deep learning model trained on human-labeled data.

Continue reading