Artificial Intelligence
Making machines smarter for improved safety, efficiency and comfort.
Our AI research encompasses advances in computer vision, speech and audio processing, as well as data analytics. Key research themes include improved perception based on machine learning techniques, learning control policies through model-based reinforcement learning, as well as cognition and reasoning based on learned semantic representations. We apply our work to a broad range of automotive and robotics applications, as well as building and home systems.
Quick Links
-
Researchers
Jonathan
Le Roux
Toshiaki
Koike-Akino
Ye
Wang
Tim K.
Marks
Anoop
Cherian
Chiori
Hori
Michael J.
Jones
Daniel N.
Nikovski
Gordon
Wichern
Devesh K.
Jha
Kieran
Parsons
Philip V.
Orlik
Diego
Romeres
Kyeong Jin
(K.J.)
KimWilliam S.
Yerazunis
Matthew E.
Brand
Mouhacine
Benosman
Hassan
Mansour
Arvind
Raghunathan
Petros T.
Boufounos
Suhas
Lohit
Saleh
Nabi
Hongbo
Sun
Yebin
Wang
Radu
Corcodel
Siddarth
Jain
Chungwei
Lin
Jianlin
Guo
Kuan-Chuan
Peng
Anthony
Vetro
Bingnan
Wang
Jinyun
Zhang
Jose
Amaya
Ankush
Chakrabarty
Aswin Shanmugam
Subramanian
Pu
(Perry)
WangAbraham P.
Vinod
-
Awards
-
AWARD MERL Ranked 1st Place in Cross-Subject Transfer Learning Task and 4th Place Overall at the NeurIPS2021 BEETL Competition for EEG Transfer Learning. Date: November 11, 2021
Awarded to: Niklas Smedemark-Margulies, Toshiaki Koike-Akino, Ye Wang, Deniz Erdogmus
MERL Contacts: Toshiaki Koike-Akino; Ye Wang
Research Areas: Artificial Intelligence, Signal Processing, Human-Computer InteractionBrief- The MERL Signal Processing group achieved first place in the cross-subject transfer learning task and fourth place overall in the NeurIPS 2021 BEETL AI Challenge for EEG Transfer Learning. The team included Niklas Smedemark-Margulies (intern from Northeastern University), Toshiaki Koike-Akino, Ye Wang, and Prof. Deniz Erdogmus (Northeastern University). The challenge addresses two types of transfer learning tasks for EEG Biosignals: a homogeneous transfer learning task for cross-subject domain adaptation; and a heterogeneous transfer learning task for cross-data domain adaptation. There were 110+ registered teams in this competition, MERL ranked 1st in the homogeneous transfer learning task, 7th place in the heterogeneous transfer learning task, and 4th place for the combined overall score. For the homogeneous transfer learning task, MERL developed a new pre-shot learning framework based on feature disentanglement techniques for robustness against inter-subject variation to enable calibration-free brain-computer interfaces (BCI). MERL is invited to present our pre-shot learning technique at the NeurIPS 2021 workshop.
-
AWARD Daniel Nikovski receives Outstanding Reviewer Award at NeurIPS'21 Date: October 18, 2021
Awarded to: Daniel Nikovski
MERL Contact: Daniel N. Nikovski
Research Areas: Artificial Intelligence, Machine LearningBrief- Daniel Nikovski, Group Manager of MERL's Data Analytics group, has received an Outstanding Reviewer Award from the 2021 conference on Neural Information Processing Systems (NeurIPS'21). NeurIPS is the world's premier conference on neural networks and related technologies.
-
AWARD Best Poster Award and Best Video Award at the International Society for Music Information Retrieval Conference (ISMIR) 2020 Date: October 15, 2020
Awarded to: Ethan Manilow, Gordon Wichern, Jonathan Le Roux
MERL Contacts: Jonathan Le Roux; Gordon Wichern
Research Areas: Artificial Intelligence, Machine Learning, Speech & AudioBrief- Former MERL intern Ethan Manilow and MERL researchers Gordon Wichern and Jonathan Le Roux won Best Poster Award and Best Video Award at the 2020 International Society for Music Information Retrieval Conference (ISMIR 2020) for the paper "Hierarchical Musical Source Separation". The conference was held October 11-14 in a virtual format. The Best Poster Awards and Best Video Awards were awarded by popular vote among the conference attendees.
The paper proposes a new method for isolating individual sounds in an audio mixture that accounts for the hierarchical relationship between sound sources. Many sounds we are interested in analyzing are hierarchical in nature, e.g., during a music performance, a hi-hat note is one of many such hi-hat notes, which is one of several parts of a drumkit, itself one of many instruments in a band, which might be playing in a bar with other sounds occurring. Inspired by this, the paper re-frames the audio source separation problem as hierarchical, combining similar sounds together at certain levels while separating them at other levels, and shows on a musical instrument separation task that a hierarchical approach outperforms non-hierarchical models while also requiring less training data. The paper, poster, and video can be seen on the paper page on the ISMIR website.
- Former MERL intern Ethan Manilow and MERL researchers Gordon Wichern and Jonathan Le Roux won Best Poster Award and Best Video Award at the 2020 International Society for Music Information Retrieval Conference (ISMIR 2020) for the paper "Hierarchical Musical Source Separation". The conference was held October 11-14 in a virtual format. The Best Poster Awards and Best Video Awards were awarded by popular vote among the conference attendees.
See All Awards for Artificial Intelligence -
-
News & Events
-
NEWS MERL researchers presented 5 papers and an invited workshop talk at ICRA 2022 Date: May 23, 2022 - May 27, 2022
Where: International Conference on Robotics and Automation (ICRA)
MERL Contacts: Ankush Chakrabarty; Stefano Di Cairano; Siddarth Jain; Devesh K. Jha; Pedro Miraldo; Daniel N. Nikovski; Rien Quirynen; Arvind Raghunathan; Diego Romeres; Abraham P. Vinod; Yebin Wang
Research Areas: Artificial Intelligence, Machine Learning, RoboticsBrief- MERL researchers presented 5 papers at the IEEE International Conference on Robotics and Automation (ICRA) that was held in Philadelphia from May 23-27, 2022. The papers covered a broad range of topics from manipulation, tactile sensing, planning and multi-agent control. The invited talk was presented in the "Workshop on Collaborative Robots and Work of the Future" which covered some of the work done by MERL researchers on collaborative robotic assembly. The workshop was co-organized by MERL, Mitsubishi Electric Automation's North America Development Center (NADC), and MIT.
-
NEWS MERL presenting 8 papers at ICASSP 2022 Date: May 22, 2022 - May 27, 2022
Where: Singapore
MERL Contacts: Anoop Cherian; Chiori Hori; Toshiaki Koike-Akino; Jonathan Le Roux; Tim K. Marks; Philip V. Orlik; Kuan-Chuan Peng; Pu (Perry) Wang; Gordon Wichern
Research Areas: Artificial Intelligence, Computer Vision, Signal Processing, Speech & AudioBrief- MERL researchers are presenting 8 papers at the IEEE International Conference on Acoustics, Speech & Signal Processing (ICASSP), which is being held in Singapore from May 22-27, 2022. A week of virtual presentations also took place earlier this month.
Topics to be presented include recent advances in speech recognition, audio processing, scene understanding, computational sensing, and classification.
ICASSP is the flagship conference of the IEEE Signal Processing Society, and the world's largest and most comprehensive technical conference focused on the research advances and latest technological development in signal and information processing. The event attracts more than 2000 participants each year.
- MERL researchers are presenting 8 papers at the IEEE International Conference on Acoustics, Speech & Signal Processing (ICASSP), which is being held in Singapore from May 22-27, 2022. A week of virtual presentations also took place earlier this month.
See All News & Events for Artificial Intelligence -
-
Research Highlights
-
Internships
-
MS1866: Deep Unsupervised/Semi-Supervised Learning for Smart Buildings
MERL is seeking a highly motivated and qualified intern to collaborate with the Multiphysical Systems (MS) team in research on unsupervised/semi-supervised learning using data from real building energy systems. The ideal candidate is expected to be working towards a Ph.D. in deep learning for time-series, with special interest in learning representations for deep clustering. Fluency in Python and either PyTorch/Tensorflow is required. Previous peer-reviewed publications in related research topics and/or experience with mining from real-world data is preferred. The minimum duration of the internship is 12 weeks; start time is flexible.
-
CA1728: Safe data-driven control of dynamical systems under uncertainty
MERL is looking for a highly motivated individual to work on safe control of data-driven, uncertain, dynamical systems. The research will develop novel optimization and learning-based control algorithms to guarantee safety and performance in various industrial applications, including autonomous driving. The ideal candidate should have experience in either one or multiple of the following topics: optimal control under uncertainty, (robust and stochastic) model predictive control, (convex and non-convex) optimization, and (reinforcement and statistical) learning. Ph.D. students in engineering or mathematics with a focus on control, optimization, and learning are encouraged to apply. A successful internship will result in submission of relevant results to peer-reviewed conference proceedings and journals, and development of well-documented (Python/MATLAB) code for MERL. The expected duration of the internship is 3-6 months, and the start date is Summer 2022.
-
ST1750: THz (Terahertz) Sensing
The Signal Processing (SP) group at MERL is seeking a highly motivated intern to conduct fundamental research in THz (Terahertz) sensing. Expertise in statistical inference, unsupervised anomaly detection, and deep learning (spatial-temporal representation learning) is required. Previous hands-on experience in THz data analysis is a plus. Familiarity with python and deep learning libraries is a must. The intern will collaborate with a small group of MERL researchers to develop novel algorithms, design experiments with collaborators, and prepare results for patents and publication. The expected duration of the internship is 3 months with a flexible start date.
See All Internships for Artificial Intelligence -
-
Recent Publications
- "AutoVAE: Mismatched Variational Autoencoder with Irregular Posterior Prior Pairing", IEEE International Symposium on Information Theory (ISIT), July 2022.BibTeX TR2022-071 PDF Video Presentation
- @inproceedings{Koike-Akino2022jul,
- author = {Koike-Akino, Toshiaki and Wang, Ye},
- title = {AutoVAE: Mismatched Variational Autoencoder with Irregular Posterior Prior Pairing},
- booktitle = {IEEE International Symposium on Information Theory (ISIT)},
- year = 2022,
- month = jul,
- url = {https://www.merl.com/publications/TR2022-071}
- }
, - "An Empirical Analysis of Boosting Deep Networks", International Joint Conference on Neural Networks (IJCNN), July 2022.BibTeX TR2022-075 PDF Presentation
- @inproceedings{Rambhatla2022jul,
- author = {Rambhatla, Sai and Jones, Michael J. and Chellappa, Rama},
- title = {An Empirical Analysis of Boosting Deep Networks},
- booktitle = {International Joint Conference on Neural Networks (IJCNN)},
- year = 2022,
- month = jul,
- url = {https://www.merl.com/publications/TR2022-075}
- }
, - "Disentangled surrogate task learning for improved domain generalization in unsupervised anomolous sound detection," Tech. Rep. TR2022-092, Detection and Classification of Acoustic Scenes and Events (DCASE) Challenge 2022, July 2022.BibTeX TR2022-092 PDF
- @techreport{Venkatesh2022jul,
- author = {Venkatesh, Satvik and Wichern, Gordon and Subramanian, Aswin Shanmugam and Le Roux, Jonathan},
- title = {Disentangled surrogate task learning for improved domain generalization in unsupervised anomolous sound detection},
- institution = {DCASE2022 Challenge},
- year = 2022,
- month = jul,
- url = {https://www.merl.com/publications/TR2022-092}
- }
, - "AutoQML: Automated Quantum Machine Learning for Wi-Fi Integrated Sensing and Communications", IEEE Sensor Array and Multichannel Signal Processing Workshop (SAM), June 2022.BibTeX TR2022-068 PDF Video Presentation
- @inproceedings{Koike-Akino2022jun,
- author = {Koike-Akino, Toshiaki and Wang, Pu and Wang, Ye},
- title = {AutoQML: Automated Quantum Machine Learning for Wi-Fi Integrated Sensing and Communications},
- booktitle = {IEEE Sensor Array and Multichannel Signal Processing Workshop (SAM)},
- year = 2022,
- month = jun,
- url = {https://www.merl.com/publications/TR2022-068}
- }
, - "PointMotionNet: Point-Wise Motion Learning for Large-Scale LiDAR Point Clouds Sequences", CVPR Workshop on Autonomous Driving, June 2022.BibTeX TR2022-083 PDF
- @inproceedings{Sullivan2022jun,
- author = {Sullivan, Alan and Wang, Jun and Li, Xiaolong and Chen, Siheng and Abbot, Lynn},
- title = {PointMotionNet: Point-Wise Motion Learning for Large-Scale LiDAR Point Clouds Sequences},
- booktitle = {CVPR Workshop on Autonomous Driving},
- year = 2022,
- month = jun,
- url = {https://www.merl.com/publications/TR2022-083}
- }
, - "Quantifying Predictive Uncertainty for Stochastic Video Synthesis from Audio", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2022.BibTeX TR2022-082 PDF
- @inproceedings{Chatterjee2022jun,
- author = {Chatterjee, Moitreya and Ahuja, Narendra and Cherian, Anoop},
- title = {Quantifying Predictive Uncertainty for Stochastic Video Synthesis from Audio},
- booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
- year = 2022,
- month = jun,
- url = {https://www.merl.com/publications/TR2022-082}
- }
,
- "AutoVAE: Mismatched Variational Autoencoder with Irregular Posterior Prior Pairing", IEEE International Symposium on Information Theory (ISIT), July 2022.
-
Videos
-
[MERL Seminar Series Spring 2022] Self-Supervised Scene Representation Learning
-
[MERL Seminar Series Spring 2022] Learning Speech Representations with Multimodal Self-Supervision
-
[MERL Seminar Series 2021] Deep probabilistic regression
-
[MERL Seminar Series 2021] Learning to See by Moving: Self-supervising 3D scene representations for perception, control, and visual reasoning
-
[MERL Seminar Series 2021] Look and Listen: From Semantic to Spatial Audio-Visual Perception
-
Application of Deep Learning for Nanophotonic Device Design (Invited)
-
Machine Learning Power Amplifier
-
Scene-Aware Interaction Technology
-
-
Software Downloads
-
SOurce-free Cross-modal KnowledgE Transfer
-
Instance Segmentation GAN
-
Audio Visual Scene-Graph Segmentor
-
Goal directed RL with Safety Constraints
-
Hierarchical Musical Instrument Separation
-
Generating Visual Dynamics from Sound and Context
-
Adversarially-Contrastive Optimal Transport
-
Online Feature Extractor Network
-
MotionNet
-
FoldingNet++
-
Quasi-Newton Trust Region Policy Optimization
-
Landmarks’ Location, Uncertainty, and Visibility Likelihood
-
Robust Iterative Data Estimation
-
Gradient-based Nikaido-Isoda
-
Discriminative Subspace Pooling
-