IBM Research AI at IJCAI-ECAI 2018

Share this post:

The 27th International Joint Conference on Artificial Intelligence and the 23rd European Conference on Artificial Intelligence (IJCAI-ECAI 2018) takes place July 13–19 in Stockholm, Sweden. IJCAI-ECAI is part of the Federated AI Meeting (FAIM), which also includes the International Conference on Autonomous Agents and Multiagent Systems (AAMAS), the International Conference on Machine Learning (ICML), the International Conference on Case-Based Reasoning (ICCBR) and the Symposium on Combinatorial Search (SoCS). IJCAI-ECAI 2018 received a record 4,000 scientific submissions, of which 800 were accepted. IBM Research AI is a silver sponsor of IJCAI-ECAI 2018 and will present technical papers and demos showcasing advances across our research portfolio. Please plan to attend the sessions listed below, and visit booth B02:16A in the exhibit hall to learn more about our AI research via videos and interactive demos:

  • Attack imaginary banks’ AI check image processing systems by distorting check digits and learn how IBM is working on mechanisms for judging the robustness of neural networks. Play our game to see how much you can maximize your profits!
  • Watch the Scenario Planning Advisor in action. Our interactive, cognitive decision-support system helps analysts to identify risk drivers and predict future scenarios, giving them foresight to mitigate unwanted outcomes and to encourage desired outcomes.
  • Learn the story of our Brain-Inspired Computing team’s work on detection and prediction of epileptic seizures using AI. Our augmented reality demo is built to run on the Microsoft HoloLens device.
  • View our neurobionics demo showcasing a brain-computer interface that combines brain analytics and 3D computer vision to perform robotic grasping. The system decodes brain signals using EEG and deep learning.

Accepted papers at IJCAI-ECAI 2018

Investigation Planning in Data Analysis
I. Lee, S. Sohrabi, A. Riabov and O. Udrea
Jul 13 16:40 – 17:00, Goal Reasoning Workshop (GRW)

On the Complexity of Quantum Circuit Compilation
A. Botea, A. Kishimoto and R. Marinescu
Jul 15 14:40 – 14:55, Symposium on Combinatorial Search (SoCS)

Computational Social Choice Meets Databases
B. Kimelfeld, P. G. Kolaitis and J. Stoyanovich
Jul 16 16:40 – 17:55

Scheduled Policy Optimization for Natural Language Communication with Intelligent Agents
W. Xiong, X. Guo, M. Yu, S. Chang, B. Zhou and W. Y. Wang
Jul 17 08:30 – 09:55

LTL Realizability via Safety and Reachability Games
A. Camacho, C. J. Muise, J. A. Baier and S. A. McIlraith
Jul 17 16:40 – 18:20

GraspNet: An Efficient Convolutional Neural Network for Real-time Grasp Detection for Low-Powered Devices
U. Asif, J. Tang and S. Harrer
Jul 18 08:30 – 09:55

Drug Similarity Integration Through Attentive Multi-View Graph Auto-Encoders
T. Ma, C. Xiao, J. Zhou and F. Wang
Jul 18 11:20 – 12:45

Managing Communication Costs under Temporal Uncertainty
N. Bhargava, C. Muise, T. Vaquero and B. Williams
Jul 18 11:20 – 13:00

Stochastic Anytime Search for Bounding Marginal MAP
R. Marinescu, R. Dechter and A. Ihler
Jul 18 14:55 – 16:10

Variable-Delay Controllability
N. Bhargava, C. Muise and B. Williams
Jul 18 16:40 – 18:20

Demos at IJCAI-ECAI 2018

Using Contextual Bandits with Behavioral Constraints for Constrained Online Movie Recommendation
A. Balakrishnan, D. Bouneffouf, N. Mattei and F. Rossi
Jul 17, morning

IBM Scenario Planning Advisor: Plan Recognition as AI Planning in Practice
S. Sohrabi, M. Katz, O. Hassanzadeh, O. Udrea and M. D. Feblowitz
Jul 17, afternoon

SynKit: LTL Synthesis as a Service
A. Camacho, C. Muise, J. Baier and S. McIlraith
Jul 18, afternoon

Semantic Representation of Data Science Programs
E. Patterson, I. Baldini, A. Mojsilovic and K. Varshney
Jul 18

More AI stories

MIT-IBM Watson AI Lab Welcomes Inaugural Members

Two years in, and the MIT-IBM Watson AI Lab is now engaging with leading companies to advance AI research. Today, the Lab announced its new Membership Program with Boston Scientific, Nexplore, Refinitiv and Samsung as the first companies to join.

Continue reading

Adversarial Robustness 360 Toolbox v1.0: A Milestone in AI Security

IBM researchers published the first major release of the Adversarial Robustness 360 Toolbox (ART). Initially released in April 2018, ART is an open-source library for adversarial machine learning that provides researchers and developers with state-of-the-art tools to defend and verify AI models against adversarial attacks. ART addresses growing concerns about people’s trust in AI, specifically the security of AI in mission-critical applications.

Continue reading

Making Sense of Neural Architecture Search

It is no surprise that following the massive success of deep learning technology in solving complicated tasks, there is a growing demand for automated deep learning. Even though deep learning is a highly effective technology, there is a tremendous amount of human effort that goes into designing a deep learning algorithm.

Continue reading