Machine Learning
Data-driven approaches to design intelligent algorithms.
MERL has a long history of research activity in machine learning, including the development of various boosting algorithms and contributing to the theory and practice of highly scalable collaborative filtering. Our recent work has focused on deep learning and reinforcement learning, with application to a wide range of applications including automotive, robotics, factory automation, transportation, as well as building and home systems.
Quick Links
-
Researchers
Takaaki
Hori
Jonathan
Le Roux
Michael
Jones
Tim
Marks
Devesh
Jha
Philip
Orlik
Anoop
Cherian
Chiori
Hori
Toshiaki
Koike-Akino
Yebin
Wang
Daniel
Nikovski
Diego
Romeres
Ye
Wang
Gordon
Wichern
Alan
Sullivan
Karl
Berntorp
Niko
Moritz
Arvind
Raghunathan
Jeroen
van Baar
Ankush
Chakrabarty
Stefano
Di Cairano
Mouhacine
Benosman
Hassan
Mansour
Uroš
Kalabić
Rien
Quirynen
Hongbo
Sun
Bingnan
Wang
Pu
(Perry)
Wang
Petros
Boufounos
Siheng
Chen
Keisuke
Kojima
Kieran
Parsons
William
Yerazunis
Matthew
Brand
Radu
Corcodel
Claus
Danielson
Bret
Harsham
Kyeong Jin
(K.J.)
Kim
Chungwei
Lin
Dehong
Liu
Jinyun
Zhang
Jianlin
Guo
Hiroyuki
Hashimoto
Emil
Laftchiev
Suhas
Lohit
Rui
Ma
Koon Hoo
Teo
Jing
Zhang
Siddarth
Jain
Takashi
Morimoto
Kuan-Chuan
Peng
Kazuto
Sugimoto
-
Awards
-
AWARD Best Paper Award at the IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) 2019 Date: December 18, 2019
Awarded to: Xuankai Chang, Wangyou Zhang, Yanmin Qian, Jonathan Le Roux, Shinji Watanabe
MERL Contact: Jonathan Le Roux
Research Areas: Artificial Intelligence, Machine Learning, Speech & AudioBrief- MERL researcher Jonathan Le Roux and co-authors Xuankai Chang, Shinji Watanabe (Johns Hopkins University), Wangyou Zhang, and Yanmin Qian (Shanghai Jiao Tong University) won the Best Paper Award at the 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU 2019), for the paper "MIMO-Speech: End-to-End Multi-Channel Multi-Speaker Speech Recognition". MIMO-Speech is a fully neural end-to-end framework that can transcribe the text of multiple speakers speaking simultaneously from multi-channel input. The system is comprised of a monaural masking network, a multi-source neural beamformer, and a multi-output speech recognition model, which are jointly optimized only via an automatic speech recognition (ASR) criterion. The award was received by lead author Xuankai Chang during the conference, which was held in Sentosa, Singapore from December 14-18, 2019.
-
AWARD MERL Researchers win Best Paper Award at ICCV 2019 Workshop on Statistical Deep Learning in Computer Vision Date: October 27, 2019
Awarded to: Abhinav Kumar, Tim K. Marks, Wenxuan Mou, Chen Feng, Xiaoming Liu
MERL Contact: Tim Marks
Research Areas: Artificial Intelligence, Computer Vision, Machine LearningBrief- MERL researcher Tim Marks, former MERL interns Abhinav Kumar and Wenxuan Mou, and MERL consultants Professor Chen Feng (NYU) and Professor Xiaoming Liu (MSU) received the Best Oral Paper Award at the IEEE/CVF International Conference on Computer Vision (ICCV) 2019 Workshop on Statistical Deep Learning in Computer Vision (SDL-CV) held in Seoul, Korea. Their paper, entitled "UGLLI Face Alignment: Estimating Uncertainty with Gaussian Log-Likelihood Loss," describes a method which, given an image of a face, estimates not only the locations of facial landmarks but also the uncertainty of each landmark location estimate.
-
AWARD MERL Researcher Devesh Jha Wins the Rudolf Kalman Best Paper Award 2019 Date: October 10, 2019
Awarded to: Devesh Jha, Nurali Virani, Zhenyuan Yuan, Ishana Shekhawat and Asok Ray
MERL Contact: Devesh Jha
Research Areas: Artificial Intelligence, Control, Data Analytics, Machine Learning, RoboticsBrief- MERL researcher Devesh Jha has won the Rudolf Kalman Best Paper Award 2019 for the paper entitled "Imitation of Demonstrations Using Bayesian Filtering With Nonparametric Data-Driven Models". This paper, published in a Special Commemorative Issue for Rudolf E. Kalman in the ASME JDSMC in March 2018, uses Bayesian filtering for imitation learning in Hidden Mode Hybrid Systems. This award is given annually by the Dynamic Systems and Control Division of ASME to the authors of the best paper published in the ASME Journal of Dynamic Systems Measurement and Control during the preceding year.
See All Awards for Machine Learning -
-
News & Events
-
TALK Universal Differential Equations for Scientific Machine Learning Date & Time: Thursday, May 7, 2020; 12:00 PM
Speaker: Christopher Rackauckas, MIT
MERL Host: Christopher Laughman
Research Areas: Machine Learning, Multi-Physical Modeling, OptimizationBrief- In the context of science, the well-known adage "a picture is worth a thousand words" might well be "a model is worth a thousand datasets." Scientific models, such as Newtonian physics or biological gene regulatory networks, are human-driven simplifications of complex phenomena that serve as surrogates for the countless experiments that validated the models. Recently, machine learning has been able to overcome the inaccuracies of approximate modeling by directly learning the entire set of nonlinear interactions from data. However, without any predetermined structure from the scientific basis behind the problem, machine learning approaches are flexible but data-expensive, requiring large databases of homogeneous labeled training data. A central challenge is reco nciling data that is at odds with simplified models without requiring "big data". In this talk we discuss a new methodology, universal differential equations (UDEs), which augment scientific models with machine-learnable structures for scientifically-based learning. We show how UDEs can be utilized to discover previously unknown governing equations, accurately extrapolate beyond the original data, and accelerate model simulation, all in a time and data-efficient manner. This advance is coupled with open-source software that allows for training UDEs which incorporate physical constraints, delayed interactions, implicitly-defined events, and intrinsic stochasticity in the model. Our examples show how a diverse set of computationally-difficult modeling issues across scientific disciplines, from automatically discovering biological mechanisms to accelerating climate simulations by 15,000x, can be handled by training UDEs.
-
TALK A Prospect in Wireless Connectivity Beyond 5G: Heterogeneity, Learning, Caution, and New Opportunities Date & Time: Thursday, May 7, 2020; 11:00 AM
Speaker: Prof. Petar Popovski, Aalborg University, Denmark
MERL Host: Toshiaki Koike-Akino
Research Areas: Artificial Intelligence, Communications, Machine Learning, Signal Processing, Information SecurityBrief
The wireless landscape evolves towards supporting a large population of connections for humans and machines with very diverse features and requirements. Perhaps the main motivation of 5G wireless systems is its flexibility to support heterogeneous connectivity requirements: enhanced mobile broadband (eMBB), massive machine-type communications (mMTC), and ultra-reliable low-latency communications (URLLC). However, this classification is rather limited and is currently undergoing a revision within the research community. The first part of this talk will discuss how this heterogeneity can be revised and which opportunities it opens with respect to spectrum usage. The second part of the talk will deal with performance guarantees of wireless services and, specifically, ultra-reliable communication and outline the importance of machine learning in that context. The final part of the talk will provide a broader view on the evolution of wireless connectivity, including aspects that are implied by the resistance to the deployment of 5G, but also the new opportunities that can transform the way we build and utilize connected systems.
See All News & Events for Machine Learning -
-
Research Highlights
-
Internships
-
CA1399: Optimization Algorithms for Stochastic Predictive Control
MERL is looking for a highly motivated individual to work on tailored numerical optimization algorithms and applications of stochastic learning-based model predictive control (MPC) methods. The research will involve the study and development of novel optimization techniques and/or the implementation and validation of algorithms for industrial applications, e.g., related to autonomous driving. The ideal candidate should have experience in either one or multiple of the following topics: stochastic MPC (e.g., scenario trees or tube MPC), convex and non-convex optimization, machine learning, numerical optimization and (inverse) optimal control. PhD students in engineering or mathematics with a focus on stochastic (learning-based) MPC or numerical optimization are encouraged to apply. Publication of relevant results in conference proceedings and journals is expected. Capability of implementing the designs and algorithms in Matlab is expected; coding parts of the algorithms in C/C++ is a plus. The expected duration of the internship is 3-6 months and the start date is flexible.
-
MD1377: Adaptive Optimal Control of Electrical Machines
MERL is seeking a motivated and qualified individual to conduct research in control of electrical machines. The ideal candidate should have solid backgrounds in adaptive dynamic programming and state/parameter estimation for electrical machines, demonstrated capability to publish results in leading conferences/journals, and experience with real-time control experiments involving high power devices. Senior Ph.D. students are encouraged to apply. Start date for this internship is flexible and the duration is about 3 months.
-
MD1300: Compiler Optimizations for Linear Algebra Kernels
MERL is looking for a highly motivated individual to work on automatic, compiler based techniques for optimizing linear algebra kernels. The ideal candidate is a Ph.D. student in computer science with extensive experience in compiler design and source code optimization techniques. In particular, the successful candidate will have a strong working knowledge of polyhedral optimization techniques, the LLVM compiler, and Polly. Strong C/C++ skills and knowledge of LLVM at the source level are required. Publication of results in conference proceedings and journals is expected. The expected duration of the internship is 3 months and the start date is flexible.
See All Internships for Machine Learning -
-
Recent Publications
- , "3D Point Cloud Processing and Learning for Autonomous Driving", IEEE Signal Processing Magazine, May 2020.BibTeX TR2020-066 PDF
- @article{Chen2020may2,
- author = {Chen, Siheng and Liu, Baoan and Feng, Chen and Vallespi-Gonzalez, Carlos and Wellington, Carl},
- title = {3D Point Cloud Processing and Learning for Autonomous Driving},
- journal = {IEEE Signal Processing Magazine},
- year = 2020,
- month = may,
- url = {https://www.merl.com/publications/TR2020-066}
- }
- , "Local Policy Optimization for Trajectory-Centric Reinforcement Learning", IEEE International Conference on Robotics and Automation (ICRA), Ayanna Howard, Eds., , May 2020, pp. 5094-5100.BibTeX TR2020-062 PDF
- @inproceedings{Jha2020may,
- author = {Jha, Devesh and Kolaric, Patrik and Raghunathan, Arvind and Lewis, Frank and Benosman, Mouhacine and Romeres, Diego and Nikovski, Daniel N.},
- title = {Local Policy Optimization for Trajectory-Centric Reinforcement Learning},
- booktitle = {IEEE International Conference on Robotics and Automation (ICRA)},
- year = 2020,
- editor = {Ayanna Howard},
- pages = {5094--5100},
- month = may,
- publisher = {IEEE},
- isbn = {978-1-7281-7395-5},
- url = {https://www.merl.com/publications/TR2020-062}
- }
- , "Fingerprinting-Based Outdoor Localization with 28-GHz Channel Measurement: A Field Study", IEEE International Workshop on Signal Processing Advances in Wireless Communications (SPAWC), May 2020.BibTeX TR2020-056 PDF
- @inproceedings{Sun2020may,
- author = {Sun, Haijian and Wang, Pu and Pajovic, Milutin and Koike-Akino, Toshiaki and Orlik, Philip V. and Taira, Akinori and Nakagawa, Kenji},
- title = {Fingerprinting-Based Outdoor Localization with 28-GHz Channel Measurement: A Field Study},
- booktitle = {IEEE International Workshop on Signal Processing Advances in Wireless Communications (SPAWC)},
- year = 2020,
- month = may,
- url = {https://www.merl.com/publications/TR2020-056}
- }
- , "Fingerprinting-Based Indoor Localization with Commercial MMWave WiFi: A Deep Learning Approach", IEEE Access, DOI: 10.1109/ACCESS.2020.2991129, April 2020.BibTeX TR2020-054 PDF Data
- @article{Koike-Akino2020apr,
- author = {Koike-Akino, Toshiaki and Wang, Pu and Pajovic, Milutin and Sun, Haijian and Orlik, Philip V.},
- title = {Fingerprinting-Based Indoor Localization with Commercial MMWave WiFi: A Deep Learning Approach},
- journal = {IEEE Access},
- year = 2020,
- month = apr,
- doi = {10.1109/ACCESS.2020.2991129},
- issn = {2169-3536},
- url = {https://www.merl.com/publications/TR2020-054}
- }
- , "Learning Invariant Representations from EEG via Adversarial Inference", IEEE Access, DOI: 10.1109/ACCESS.2020.2971600, Vol. 8, pp. 27074-27085, April 2020.BibTeX TR2020-049 PDF
- @article{Ozdenizci2020apr,
- author = {Ozdenizci, Ozan and Wang, Ye and Koike-Akino, Toshiaki and Erdogmus, Deniz},
- title = {Learning Invariant Representations from EEG via Adversarial Inference},
- journal = {IEEE Access},
- year = 2020,
- volume = 8,
- pages = {27074--27085},
- month = apr,
- doi = {10.1109/ACCESS.2020.2971600},
- issn = {2169-3536},
- url = {https://www.merl.com/publications/TR2020-049}
- }
- , "Learning Plug-and-Play Proximal Quasi-Newton Denoisers", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/ICASSP40776.2020.9054537, April 2020, pp. 8896-8900.BibTeX TR2020-045 PDF Video
- @inproceedings{Al-Shabili2020apr,
- author = {Al-Shabili, Abdullah and Mansour, Hassan and Boufounos, Petros T.},
- title = {Learning Plug-and-Play Proximal Quasi-Newton Denoisers},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2020,
- pages = {8896--8900},
- month = apr,
- publisher = {IEEE},
- doi = {10.1109/ICASSP40776.2020.9054537},
- issn = {2379-190X},
- isbn = {978-1-5090-6631-5},
- url = {https://www.merl.com/publications/TR2020-045}
- }
- , "End-To-End Multi-Speaker Speech Recognition with Transformer", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/ICASSP40776.2020.9054029, April 2020, pp. 6134-6138.BibTeX TR2020-043 PDF Video
- @inproceedings{Chang2020apr,
- author = {Chang, Xuankai and Zhang, Wangyou and Qian, Yanmin and Le Roux, Jonathan and Watanabe, Shinji},
- title = {End-To-End Multi-Speaker Speech Recognition with Transformer},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2020,
- pages = {6134--6138},
- month = apr,
- publisher = {IEEE},
- doi = {10.1109/ICASSP40776.2020.9054029},
- issn = {2379-190X},
- isbn = {978-1-5090-6631-5},
- url = {https://www.merl.com/publications/TR2020-043}
- }
- , "WHAMR!: Noisy and Reverberant Single-Channel Speech Separation", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/ICASSP40776.2020.9053327, April 2020, pp. 696-700.BibTeX TR2020-042 PDF Video
- @inproceedings{Maciejewski2020apr,
- author = {Maciejewski, Matthew and Wichern, Gordon and McQuinn, Emmett and Le Roux, Jonathan},
- title = {WHAMR!: Noisy and Reverberant Single-Channel Speech Separation},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2020,
- pages = {696--700},
- month = apr,
- publisher = {IEEE},
- doi = {10.1109/ICASSP40776.2020.9053327},
- issn = {2379-190X},
- isbn = {978-1-5090-6631-5},
- url = {https://www.merl.com/publications/TR2020-042}
- }
- , "3D Point Cloud Processing and Learning for Autonomous Driving", IEEE Signal Processing Magazine, May 2020.
-
Videos
-
Software Downloads
