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
Jonathan
Le Roux
Takaaki
Hori
Toshiaki
Koike-Akino
Devesh
Jha
Michael
Jones
Tim
Marks
Ye
Wang
Anoop
Cherian
Philip
Orlik
Daniel
Nikovski
Gordon
Wichern
Chiori
Hori
Diego
Romeres
Yebin
Wang
Karl
Berntorp
Alan
Sullivan
Niko
Moritz
Stefano
Di Cairano
Ankush
Chakrabarty
Kieran
Parsons
Jeroen
van Baar
Keisuke
Kojima
Arvind
Raghunathan
Pu
(Perry)
Wang
Hassan
Mansour
Bingnan
Wang
Mouhacine
Benosman
Petros
Boufounos
Uroš
Kalabić
Rien
Quirynen
Kyeong Jin
(K.J.)
Kim
Hongbo
Sun
Radu
Corcodel
Jianlin
Guo
William
Yerazunis
Matthew
Brand
Chungwei
Lin
Dehong
Liu
Suhas
Lohit
Rui
Ma
Marcel
Menner
Jing
Zhang
Jinyun
Zhang
Siddarth
Jain
Christopher
Laughman
Yanting
Ma
Koon Hoo
Teo
Anthony
Vetro
Varun
Haritsa
Kuan-Chuan
Peng
Abraham
P. Vinod
-
Awards
-
AWARD Excellent Presentation Award Date: January 25, 2021
Awarded to: Takenori Sumi, Yukimasa Nagai, Jianlin Guo, Philip Orlik, Tatsuya Yokoyama, Hiroshi Mineno
MERL Contacts: Jianlin Guo; Philip Orlik
Research Areas: Communications, Machine Learning, Signal ProcessingBrief- MELCO and MERL researchers have won "Excellent Presentation Award" at the IPSJ/CDS30 (Information Processing Society of Japan/Consumer Devices and Systems 30th conferences) held on January 25, 2021. The paper titled "Sub-1 GHz Coexistence Using Reinforcement Learning Based IEEE 802.11ah RAW Scheduling" addresses coexistence between IEEE 802.11ah and IEEE 802.15.4g systems in the Sub-1 GHz frequency bands. This paper proposes a novel method to allocate IEEE 802.11 RAW time slots using a Q-Learning technique. MERL and MELCO have been leading IEEE 802.19.3 coexistence standard development and this paper is a good candidate for future standard enhancement. The authors are Takenori Sumi, Yukimasa Nagai, Jianlin Guo, Philip Orlik, Tatsuya Yokoyama and Hiroshi Mineno.
-
AWARD Best Paper - Honorable Mention Award at WACV 2021 Date: January 6, 2021
Awarded to: Rushil Anirudh, Suhas Lohit, Pavan Turaga
MERL Contact: Suhas Lohit
Research Areas: Computational Sensing, Computer Vision, Machine LearningBrief- A team of researchers from Mitsubishi Electric Research Laboratories (MERL), Lawrence Livermore National Laboratory (LLNL) and Arizona State University (ASU) received the Best Paper Honorable Mention Award at WACV 2021 for their paper "Generative Patch Priors for Practical Compressive Image Recovery".
The paper proposes a novel model of natural images as a composition of small patches which are obtained from a deep generative network. This is unlike prior approaches where the networks attempt to model image-level distributions and are unable to generalize outside training distributions. The key idea in this paper is that learning patch-level statistics is far easier. As the authors demonstrate, this model can then be used to efficiently solve challenging inverse problems in imaging such as compressive image recovery and inpainting even from very few measurements for diverse natural scenes.
- A team of researchers from Mitsubishi Electric Research Laboratories (MERL), Lawrence Livermore National Laboratory (LLNL) and Arizona State University (ASU) received the Best Paper Honorable Mention Award at WACV 2021 for their paper "Generative Patch Priors for Practical Compressive Image Recovery".
-
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 Machine Learning -
-
News & Events
-
NEWS MERL researchers Diego Romeres, Devesh Jha and Siddarth Jain co-organized a workshop on Robotic Manipulation at the RSS 2021 conference Date: July 13, 2021
Where: Robotics: Science and Systems
MERL Contacts: Siddarth Jain; Devesh Jha; Diego Romeres
Research Areas: Artificial Intelligence, Machine Learning, RoboticsBrief- MERL researchers Diego Romeres, Devesh Jha, and Siddarth Jain together with research groups at MIT, NVIDIA, NIST, TUM, Google DeepMind, ETH Zurich, Google AI, and UMASS Lowell organized a workshop at the Robotics: Science and Systems 2021 conference. The workshop was on "Advancing Artificial Intelligence and Manipulation for Robotics: Understanding Gaps, Industry and Academic Perspectives, and Community Building". The workshop had a list of excellent speakers both from academia and industry. Recording of the talks and of the panel discussion can be found in the link below.
-
NEWS MERL and Mitsubishi Electric U.S. participating in International Microwave Symposium Week 2021 Date: June 18, 2021
MERL Contacts: Mouhacine Benosman; Rui Ma
Research Areas: Electronic and Photonic Devices, Machine Learning, Signal ProcessingBrief- During the 2021 International Microwave Symposium Week (June 20-25), Rui Ma will give an invited talk on MERL's recent power amplifiers research at an IMS Technical Workshop to be held on June 21st, titled "From Digital to Intelligent: Advancement of MISO Power Amplifiers by Machine Learning".
IMS is the annual flagship conference of IEEE MTT-S (Microwave Theory and Techniques Society) and the centerpiece of Microwave Week. It is the largest gathering of RF/Microwave professionals in the world and combines multiple technical conferences with the biggest commercial exhibitions for the microwave industry.
Mitsubishi Electric U.S. (MEUS) will also host an online interactive booth to showcase our latest high-frequency Semiconductor & Device products at IMS week.
More detailed information can be found at the Mitsubishi Electric booth.
- During the 2021 International Microwave Symposium Week (June 20-25), Rui Ma will give an invited talk on MERL's recent power amplifiers research at an IMS Technical Workshop to be held on June 21st, titled "From Digital to Intelligent: Advancement of MISO Power Amplifiers by Machine Learning".
See All News & Events for Machine Learning -
-
Research Highlights
-
Internships
-
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.
-
SP1537: Machine Learning for Wireless Communications
MERL is seeking an intern to work on machine learning for wireless communication systems. The ideal candidate would be an experienced PhD student or post-graduate researcher working in wireless communications with a focus on machine learning methods. The candidate should have a detailed knowledge of wireless communications, with some experience in machine learning, MIMO, and/or channel equalization preferred. Strong programming skills in Python and machine learning frameworks are essential. The expected duration of the internship is 3-6 months with flexible start date and length. This internship is preferred to be onsite at MERL, but may be done remotely where you live if the COVID pandemic makes it necessary.
-
CA1565: Connected Vehicle Driver Assistance Systems
MERL is seeking a highly motivated qualified intern to collaborate with the Control for Autonomy team and the Signal Processing group in the development of Advanced Driver Assistance Systems (ADAS) for Connected Vehicles. The intern will collaborate in the development of methods for distributed learning and optimization of ADAS using data-sharing between connected vehicles and infrastructure. The ideal candidate has knowledge of machine learning, optimization and connected vehicles. Knowledge of one or more traffic and/or multi-vehicle simulators (SUMO, Vissim, etc.) is a plus. Good programming skills in MATLAB, Python, or C/C++ are required. Candidates in their junior or senior years of a Ph.D. program are encouraged to apply. The expected duration of the internship is 3-6 months, starting in Spring or Summer 2021, but later starting periods may also be considered. This internship is preferred to be onsite at MERL, but may be done remotely where you live if the COVID pandemic makes it necessary.
See All Internships for Machine Learning -
-
Recent Publications
- , "Robust Machine Learning via Privacy/Rate-Distortion Theory", IEEE International Symposium on Information Theory (ISIT), July 2021.BibTeX TR2021-082 PDF Video Presentation
- @inproceedings{Wang2021jul,
- author = {Wang, Ye and Aeron, Shuchin and Rakin, Adnan S and Koike-Akino, Toshiaki and Moulin, Pierre},
- title = {Robust Machine Learning via Privacy/Rate-Distortion Theory},
- booktitle = {IEEE International Symposium on Information Theory (ISIT)},
- year = 2021,
- month = jul,
- url = {https://www.merl.com/publications/TR2021-082}
- }
- , "Multi-Task Federated Learning for Traffic Prediction and Its Application to Route Planning", IEEE Intelligent Vehicles Symposium, July 2021.BibTeX TR2021-083 PDF
- @inproceedings{Zeng2021jul,
- author = {Zeng, Tengchan and Guo, Jianlin and Kim, Kyeong Jin and Parsons, Kieran and Orlik, Philip V. and Di Cairano, Stefano and Saad, Walid},
- title = {Multi-Task Federated Learning for Traffic Prediction and Its Application to Route Planning},
- booktitle = {IEEE Intelligent Vehicles Symposium},
- year = 2021,
- month = jul,
- url = {https://www.merl.com/publications/TR2021-083}
- }
- , "Generalized One-Class Learning Using Pairs of Complementary Classifiers", IEEE Transactions on Pattern Analysis and Machine Intelligence, June 2021.BibTeX TR2021-076 PDF
- @article{Cherian2021jun,
- author = {Cherian, Anoop and Wang, Jue},
- title = {Generalized One-Class Learning Using Pairs of Complementary Classifiers},
- journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
- year = 2021,
- month = jun,
- url = {https://www.merl.com/publications/TR2021-076}
- }
- , "Control of Mechanical Systems via Feedback Linearization Based on Black-Box Gaussian Process Models", European Control Conference (ECC), June 2021.BibTeX TR2021-068 PDF
- @inproceedings{DallaLibera2021jun,
- author = {Dalla Libera, Alberto and Amadio, Fabio and Nikovski, Daniel N. and Carli, Ruggero and Romeres, Diego},
- title = {Control of Mechanical Systems via Feedback Linearization Based on Black-Box Gaussian Process Models},
- booktitle = {European Control Conference (ECC)},
- year = 2021,
- month = jun,
- url = {https://www.merl.com/publications/TR2021-068}
- }
- , "Few-Shot Bearing Fault Diagnosis Based on Model-Agnostic Meta-Learning", IEEE Transactions on Industry Applications, DOI: 10.1109/TIA.2021.3091958, June 2021.BibTeX TR2021-081 PDF
- @article{Zhang2021jun,
- author = {Zhang, Shen and Ye, Fei and Wang, Bingnan and Habetler, Thomas G},
- title = {Few-Shot Bearing Fault Diagnosis Based on Model-Agnostic Meta-Learning},
- journal = {IEEE Transactions on Industry Applications},
- year = 2021,
- month = jun,
- doi = {10.1109/TIA.2021.3091958},
- url = {https://www.merl.com/publications/TR2021-081}
- }
- , "Wireless 3D Point Cloud Delivery Using Deep Graph Neural Networks", IEEE International Conference on Communications (ICC), June 2021.BibTeX TR2021-066 PDF
- @inproceedings{Fujihashi2021jun,
- author = {Fujihashi, Takuya and Koike-Akino, Toshiaki and Chen, Siheng and Watanabe, Takashi},
- title = {Wireless 3D Point Cloud Delivery Using Deep Graph Neural Networks},
- booktitle = {IEEE International Conference on Communications (ICC)},
- year = 2021,
- month = jun,
- url = {https://www.merl.com/publications/TR2021-066}
- }
- , "Cross-domain Imitation from Observations", International Conference on Machine Learning (ICML), June 2021.BibTeX TR2021-074 PDF
- @inproceedings{Raychaudhuri2021jun,
- author = {Raychaudhuri, Dripta S. and van Baar, Jeroen and Paul, Sujoy and Roy-Chowdhury, Amit K.},
- title = {Cross-domain Imitation from Observations},
- booktitle = {International Conference on Machine Learning (ICML)},
- year = 2021,
- month = jun,
- url = {https://www.merl.com/publications/TR2021-074}
- }
- , "Capturing Multi-Resolution Context by Dilated Self-Attention", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), June 2021.BibTeX TR2021-036 PDF
- @inproceedings{Moritz2021jun,
- author = {Moritz, Niko and Hori, Takaaki and Le Roux, Jonathan},
- title = {Capturing Multi-Resolution Context by Dilated Self-Attention},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2021,
- month = jun,
- url = {https://www.merl.com/publications/TR2021-036}
- }
- , "Robust Machine Learning via Privacy/Rate-Distortion Theory", IEEE International Symposium on Information Theory (ISIT), July 2021.
-
Videos
-
Control of Mechanical Systems via Feedback Linearization Based on Black-Box Gaussian Process Models
-
Application of Deep Learning for Nanophotonic Device Design (Invited)
-
Towards Human-Level Learning of Complex Physical Puzzles
-
Tactile-RL for Insertion: Generalization to Objects of Unknown Geometry
-
[ACP 2020] Inverse Design of Nanophotonic Devices using Deep Neural Networks
-
Action Detection Using A Deep Recurrent Neural Network
-
MERL Research on Autonomous Vehicles
-
Obstacle Detection
-
Semantic Scene Labeling
-
Deep Hierarchical Parsing for Semantic Segmentation
-
Global Local Face Upsampling Network
-
-
Software Downloads
-
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
-
Circular Maze Environment
-
Discriminative Subspace Pooling
-
Kernel Correlation Network
-
Fast Resampling on Point Clouds via Graphs
-
FoldingNet
-
Deep Category-Aware Semantic Edge Detection
-
