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
Toshiaki
Koike-Akino
Jonathan
Le Roux
Ye
Wang
Ankush
Chakrabarty
Anoop
Cherian
Philip V.
Orlik
Tim K.
Marks
Gordon
Wichern
Michael J.
Jones
Devesh K.
Jha
Stefano
Di Cairano
Daniel N.
Nikovski
Kieran
Parsons
Chiori
Hori
Karl
Berntorp
Diego
Romeres
Yebin
Wang
Pu
(Perry)
WangChristopher R.
Laughman
Mouhacine
Benosman
Matthew
Brand
Hassan
Mansour
Arvind
Raghunathan
Bingnan
Wang
Rien
Quirynen
Suhas
Lohit
Marcel
Menner
Petros T.
Boufounos
Jing
Zhang
Jianlin
Guo
Radu
Corcodel
Siddarth
Jain
Kuan-Chuan
Peng
Hongbo
Sun
Scott A.
Bortoff
Chungwei
Lin
Dehong
Liu
Saviz
Mowlavi
Hongtao
Qiao
Wataru
Tsujita
William S.
Yerazunis
Marcus
Greiff
Kei
Ota
Koon Hoo
Teo
Anthony
Vetro
Abraham P.
Vinod
Jinyun
Zhang
Jose
Amaya
Yanting
Ma
Jing
Liu
-
Awards
-
AWARD Japan Telecommunications Advancement Foundation Award Date: March 15, 2022
Awarded to: Yukimasa Nagai, Jianlin Guo, Philip Orlik, Takenori Sumi, Benjamin A. Rolfe and Hiroshi Mineno
MERL Contacts: Jianlin Guo; Philip V. Orlik
Research Areas: Communications, Machine LearningBrief- MELCO/MERL research paper “Sub-1 GHz Frequency Band Wireless Coexistence for the Internet of Things” has won the 37th Telecommunications Advancement Foundation Award (Telecom System Technology Award) in Japan. This award started in 1984, and is given to research papers and works related to information and telecommunications that have made significant contributions and achievements to the advancement, development, and standardization of information and telecommunications from technical and engineering perspectives. The award recognizes both the IEEE 802.19.3 standardization efforts and the technological advancements using reinforcement learning and robust access methodologies for wireless communication system. This year, there were 43 entries with 5 winning awards and 3 winning encouragement awards. This is the first time MELCO/MERL has received this award. Our paper has been published by IEEE Access in 2021 and authors are Yukimasa Nagai, Jianlin Guo, Philip Orlik, Takenori Sumi, Benjamin A. Rolfe and Hiroshi Mineno.
-
AWARD Mitsubishi Electric US Receives a 2022 CES Innovation Award for Touchless Elevator Control Jointly Developed with MERL Date: November 17, 2021
Awarded to: Elevators and Escalators Division of Mitsubishi Electric US, Inc.
MERL Contacts: Daniel N. Nikovski; William S. Yerazunis
Research Areas: Data Analytics, Machine Learning, Signal ProcessingBrief- The Elevators and Escalators Division of Mitsubishi Electric US, Inc. has been recognized as a 2022 CES® Innovation Awards honoree for its new PureRide™ Touchless Control for elevators, jointly developed with MERL. Sponsored by the Consumer Technology Association (CTA), the CES Innovation Awards is the largest and most influential technology event in the world. PureRide™ Touchless Control provides a simple, no-touch product that enables users to call an elevator and designate a destination floor by placing a hand or finger over a sensor. MERL initiated the development of PureRide™ in the first weeks of the COVID-19 pandemic by proposing the use of infra-red sensors for operating elevator call buttons, and participated actively in its rapid implementation and commercialization, resulting in a first customer installation in October of 2020.
-
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.
See All Awards for Machine Learning -
-
News & Events
-
TALK [MERL Seminar Series 2023] Dr. Suraj Srinivas presents talk titled Pitfalls and Opportunities in Interpretable Machine Learning Date & Time: Tuesday, March 14, 2023; 1:00 PM
Speaker: Suraj Srinivas, Harvard University
MERL Host: Suhas Lohit
Research Areas: Artificial Intelligence, Computer Vision, Machine LearningAbstractIn this talk, I will discuss our recent research on understanding post-hoc interpretability. I will begin by introducing a characterization of post-hoc interpretability methods as local function approximators, and the implications of this viewpoint, including a no-free-lunch theorem for explanations. Next, we shall challenge the assumption that post-hoc explanations provide information about a model's discriminative capabilities p(y|x) and instead demonstrate that many common methods instead rely on a conditional generative model p(x|y). This observation underscores the importance of being cautious when using such methods in practice. Finally, I will propose to resolve this via regularization of model structure, specifically by training low curvature neural networks, resulting in improved model robustness and stable gradients.
-
TALK [MERL Seminar Series 2023] Prof. Shaowu Pan presents talk titled Neural Implicit Flow Date & Time: Wednesday, March 1, 2023; 1:00 PM
Speaker: Shaowu Pan, Rensselaer Polytechnic Institute
MERL Host: Saviz Mowlavi
Research Areas: Computational Sensing, Data Analytics, Machine LearningAbstractHigh-dimensional spatio-temporal dynamics can often be encoded in a low-dimensional subspace. Engineering applications for modeling, characterization, design, and control of such large-scale systems often rely on dimensionality reduction to make solutions computationally tractable in real-time. Common existing paradigms for dimensionality reduction include linear methods, such as the singular value decomposition (SVD), and nonlinear methods, such as variants of convolutional autoencoders (CAE). However, these encoding techniques lack the ability to efficiently represent the complexity associated with spatio-temporal data, which often requires variable geometry, non-uniform grid resolution, adaptive meshing, and/or parametric dependencies. To resolve these practical engineering challenges, we propose a general framework called Neural Implicit Flow (NIF) that enables a mesh-agnostic, low-rank representation of large-scale, parametric, spatial-temporal data. NIF consists of two modified multilayer perceptrons (MLPs): (i) ShapeNet, which isolates and represents the spatial complexity, and (ii) ParameterNet, which accounts for any other input complexity, including parametric dependencies, time, and sensor measurements. We demonstrate the utility of NIF for parametric surrogate modeling, enabling the interpretable representation and compression of complex spatio-temporal dynamics, efficient many-spatial-query tasks, and improved generalization performance for sparse reconstruction.
See All News & Events for Machine Learning -
-
Research Highlights
-
Internships
-
CA1904: Numerical Optimal Control for Hybrid Dynamical Systems
MERL is looking for a highly motivated individual to work on tailored computational algorithms for numerical optimal control of hybrid dynamical systems and applications for decision making, motion planning and control of autonomous systems. The research will involve the study and development of numerical optimal control methods for systems with continuous dynamics and discrete logic, nonsmooth and/or switched dynamics, and the implementation and validation of such algorithms for industrial applications, e.g., related to autonomous driving and robotics. The ideal candidate should have experience in either one or multiple of the following topics: mixed-integer programming (MIP), mathematical programs with complementarity constraints (MPCCs), modeling and formulation of optimal control problems for hybrid dynamical systems, convex and non-convex optimization, machine learning and real-time optimization. PhD students in engineering or mathematics, especially with a focus on MIPs, MPCCs or numerical optimal control, are encouraged to apply. Publication of relevant results in conference proceedings or journals is expected. Capability of implementing the designs and algorithms in MATLAB/Python 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.
-
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.
-
MD1891: Electric machine monitoring technologies
MERL is looking for a self-motivated intern to work on electric machine monitoring, fault detection, and predictive maintenance. The ideal candidate would be a Ph.D. candidate in electrical engineering or computer science with solid research background in electric machines, signal processing, and machine learning. Proficiency in MATLAB and Simulink is necessary. The intern is expected to collaborate with MERL researchers to perform simulations, analyze experimental data, and prepare manuscripts for scientific publications. The total duration is anticipated to be 3 months and the start date is flexible. This internship requires work that can only be done at MERL.
See All Internships for Machine Learning -
-
Recent Publications
- "Travel-time prediction using neural-network-based mixture models", International Workshop on Statistical Methods and Artificial Intelligence, March 2023.BibTeX TR2023-012 PDF
- @inproceedings{Sharma2023mar,
- author = {Sharma, Abhishek and Zhang, Jing and Nikovski, Daniel and Doshi-Velez, Finale},
- title = {Travel-time prediction using neural-network-based mixture models},
- booktitle = {International Workshop on Statistical Methods and Artificial Intelligence},
- year = 2023,
- month = mar,
- url = {https://www.merl.com/publications/TR2023-012}
- }
, - "Estimating Traffic Density Using Transformer Decoders", International Workshop on Statistical Methods and Artificial Intelligence, March 2023.BibTeX TR2023-011 PDF
- @inproceedings{Wang2023mar,
- author = {Wang, Yinsong and Zhang, Jing and Nikovski, Daniel and Kojima, Takuro},
- title = {Estimating Traffic Density Using Transformer Decoders},
- booktitle = {International Workshop on Statistical Methods and Artificial Intelligence},
- year = 2023,
- month = mar,
- url = {https://www.merl.com/publications/TR2023-011}
- }
, - "Discriminative 3D Shape Modeling for Few-Shot Instance Segmentation", IEEE International Conference on Robotics and Automation (ICRA), March 2023.BibTeX TR2023-010 PDF
- @inproceedings{Cherian2023mar,
- author = {Cherian, Anoop and Jain, Siddarth and Marks, Tim K. and Sullivan, Alan},
- title = {Discriminative 3D Shape Modeling for Few-Shot Instance Segmentation},
- booktitle = {IEEE International Conference on Robotics and Automation (ICRA)},
- year = 2023,
- month = mar,
- url = {https://www.merl.com/publications/TR2023-010}
- }
, - "A System Approach for Efficiency Enhancement and Linearization Technique of Dual-Input Doherty Power Amplifier", IEEE Journal of Microwaves, February 2023.BibTeX TR2023-008 PDF
- @article{Kantana2023feb,
- author = {Kantana, Chouabi and Benosman, Mouhacine and Ma, Rui and Komatsuzaki, Y.},
- title = {A System Approach for Efficiency Enhancement and Linearization Technique of Dual-Input Doherty Power Amplifier},
- journal = {IEEE Journal of Microwaves},
- year = 2023,
- month = feb,
- url = {https://www.merl.com/publications/TR2023-008}
- }
, - "Parameter-Adaptive Reference Governors with Learned Robust Constraint-Admissible Sets", Control Engineering Practice, February 2023.BibTeX TR2023-005 PDF
- @article{Chakrabarty2023feb,
- author = {Chakrabarty, Ankush and Berntorp, Karl and Di Cairano, Stefano},
- title = {Parameter-Adaptive Reference Governors with Learned Robust Constraint-Admissible Sets},
- journal = {Control Engineering Practice},
- year = 2023,
- month = feb,
- url = {https://www.merl.com/publications/TR2023-005}
- }
, - "Inverse design of two-dimensional freeform metagrating using an adversarial conditional variational autoencoder", SPIE Photonics West, January 2023.BibTeX TR2023-004 PDF
- @inproceedings{Kojima2023jan,
- author = {Kojima, Keisuke and Koike-Akino, Toshiaki and Wang, Ye and Jung Minwoo and Brand, Matthew},
- title = {Inverse design of two-dimensional freeform metagrating using an adversarial conditional variational autoencoder},
- booktitle = {SPIE Photonics West},
- year = 2023,
- month = jan,
- url = {https://www.merl.com/publications/TR2023-004}
- }
, - "Learning a Constrained Optimizer: A Primal Method", AAAI Conference on Artificial Intelligence, January 2023.BibTeX TR2023-003 PDF
- @inproceedings{Liu2023jan,
- author = {Liu, Tao and Cherian, Anoop},
- title = {Learning a Constrained Optimizer: A Primal Method},
- booktitle = {AAAI Conference on Artificial Intelligence},
- year = 2023,
- month = jan,
- url = {https://www.merl.com/publications/TR2023-003}
- }
, - "GSR: A Generalized Symbolic Regression Approach", Transactions on Machine Learning Research, January 2023.BibTeX TR2023-002 PDF
- @article{Tohme2023jan,
- author = {Tohme, Tony and Liu, Dehong and Youcef-Toumi, Kamal},
- title = {GSR: A Generalized Symbolic Regression Approach},
- journal = {Transactions on Machine Learning Research},
- year = 2023,
- month = jan,
- url = {https://www.merl.com/publications/TR2023-002}
- }
,
- "Travel-time prediction using neural-network-based mixture models", International Workshop on Statistical Methods and Artificial Intelligence, March 2023.
-
Videos
-
[MERL Seminar Series Spring 2022] Hybrid robotics and implicit learning
-
Toshiaki Koike-Akino Gives Seminar Talk at IEEE Boston Photonics
-
[MERL Seminar Series Spring 2022] RLMPC: An Ideal Combination of Formal Optimal Control and Reinforcement Learning?
-
[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 Spring 2022] Extreme optics design as a large-scale optimization problem
-
HealthCam: A system for non-contact monitoring of vital signs
-
[MERL Seminar Series 2021] Harnessing machine learning to build better Earth system models for climate projection
-
[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
-
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
-
Scene-Aware Interaction Technology
-
Action Detection Using A Deep Recurrent Neural Network
-
Obstacle Detection
-
Semantic Scene Labeling
-
MERL Research on Autonomous Vehicles
-
Deep Hierarchical Parsing for Semantic Segmentation
-
Global Local Face Upsampling Network
-
-
Software Downloads
-
SOurce-free Cross-modal KnowledgE Transfer
-
Nonparametric Score Estimators
-
Instance Segmentation GAN
-
Audio Visual Scene-Graph Segmentor
-
Generalized One-class Discriminative Subspaces
-
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
-
Circular Maze Environment
-
Discriminative Subspace Pooling
-
Kernel Correlation Network
-
Fast Resampling on Point Clouds via Graphs
-
FoldingNet
-
Deep Category-Aware Semantic Edge Detection
-
Partial Group Convolutional Neural Networks
-