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.

  • Researchers

  • 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 & Audio
      Brief
      • 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 Learning
      Brief
      • 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, Robotics
      Brief
      • 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

    •  NEWS   MERL's Scene-Aware Interaction Technology Featured in Mitsubishi Electric Corporation Press Release
      Date: July 22, 2020
      Where: Tokyo, Japan
      MERL Contacts: Siheng Chen; Anoop Cherian; Bret Harsham; Chiori Hori; Takaaki Hori; Jonathan Le Roux; Tim Marks; Alan Sullivan; Anthony Vetro
      Research Areas: Artificial Intelligence, Computer Vision, Machine Learning, Speech & Audio
      Brief
      • Mitsubishi Electric Corporation announced that the company has developed what it believes to be the world’s first technology capable of highly natural and intuitive interaction with humans based on a scene-aware capability to translate multimodal sensing information into natural language.

        The novel technology, Scene-Aware Interaction, incorporates Mitsubishi Electric’s proprietary Maisart® compact AI technology to analyze multimodal sensing information for highly natural and intuitive interaction with humans through context-dependent generation of natural language. The technology recognizes contextual objects and events based on multimodal sensing information, such as images and video captured with cameras, audio information recorded with microphones, and localization information measured with LiDAR.

        Scene-Aware Interaction for car navigation, one target application, will provide drivers with intuitive route guidance. The technology is also expected to have applicability to human-machine interfaces for in-vehicle infotainment, interaction with service robots in building and factory automation systems, systems that monitor the health and well-being of people, surveillance systems that interpret complex scenes for humans and encourage social distancing, support for touchless operation of equipment in public areas, and much more. The technology is based on recent research by MERL's Speech & Audio and Computer Vision groups.


        Demonstration Video:



        Link:

        Mitsubishi Electric Corporation Press Release
    •  
    •  TALK   GCN-RL Circuit Designer: Transferable Transistor Sizing with Graph Neural Networks and Reinforcement Learning
      Date & Time: Tuesday, July 14, 2020; 11:00 AM
      Speaker: Hanrui Wang, MIT
      MERL Host: Rui Ma
      Research Areas: Electronic and Photonic Devices, Machine Learning
      Brief
      • Automatic transistor sizing is a challenging problem in circuit design due to the large design space, complex performance trade-offs, and fast technological advancements. Although there has been plenty of work on transistor sizing targeting on one circuit, limited research has been done on transferring the knowledge from one circuit to another to reduce the re-design overhead. In this work, we present GCN-RL Circuit Designer, leveraging reinforcement learning (RL) to transfer the knowledge between different technology nodes and topologies. Moreover, inspired by the simple fact that circuit is a graph, we learn on the circuit topology representation with graph convolutional neural networks (GCN). The GCN-RL agent extracts features of the topology graph whose vertices are transistors, edges are wires. Our learning-based optimization consistently achieves the highest Figures of Merit (FoM) on four different circuits compared with conventional black-box optimization methods (Bayesian Optimization, Evolutionary Algorithms), random search, and human expert designs. Experiments on transfer learning between five technology nodes and two circuit topologies demonstrate that RL with transfer learning can achieve much higher FoMs than methods without knowledge transfer. Our transferable optimization method makes transistor sizing and design porting more effective and efficient. The work is accepted to DAC 2020.
    •  

    See All News & Events for Machine Learning
  • Research Highlights

  • Internships

    • SP1448: Intelligent Coding

      The Signal Processing group at MERL is seeking a highly motivated, qualified individual to join our 3-month internship program of research on applied coding for data science. The ideal candidate is expected to possess an excellent background in channel coding, source coding, information theory, coded modulation design, signal processing, deep learning, quantum computing, and molecular computing.

    • MD1370: Machine Learning based DPD for Power Amplifier

      MERL is looking for a talented intern to work on the next generation Digital-predistortion algorithms for power amplifier linearization such as 5G. The development of a DPD system involves aspects of signal processing and statistical algorithm design, RF components and instrumentation, digital hardware and software. It is therefore both a challenging and intellectually rewarding experience. This will involve MATLAB coding, interfacing to test equipment such as power sources, signal generators and analyzers and construction and calibration of RF component assemblies. The ideal candidate should have knowledge and experience in adaptive signal processing, machine learning, and radio communication. Good practical laboratory skills are needed. RF semiconductor devices and circuit knowledge is a plus. Duration is 3 to 6 months.

    • 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.


    See All Internships for Machine Learning
  • Recent Publications

    •  Han, M., Ozdenizci, O., Wang, Y., Koike-Akino, T., Erdogmus, D., "Disentangled Adversarial Transfer Learning for Physiological Biosignals", International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), July 2020.
      BibTeX TR2020-109 PDF Video
      • @inproceedings{Han2020jul,
      • author = {Han, Mo and Ozdenizci, Ozan and Wang, Ye and Koike-Akino, Toshiaki and Erdogmus, Deniz},
      • title = {Disentangled Adversarial Transfer Learning for Physiological Biosignals},
      • booktitle = {International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)},
      • year = 2020,
      • month = jul,
      • url = {https://www.merl.com/publications/TR2020-109}
      • }
    •  Seetharaman, P., Wichern, G., Le Roux, J., Pardo, B., "Bootstrapping Unsupervised Deep Music Separation from Primitive Auditory Grouping Principles", ICML 2020 Workshop on Self-supervision in Audio and Speech, July 2020.
      BibTeX TR2020-111 PDF
      • @inproceedings{Seetharaman2020jul,
      • author = {Seetharaman, Prem and Wichern, Gordon and Le Roux, Jonathan and Pardo, Bryan},
      • title = {Bootstrapping Unsupervised Deep Music Separation from Primitive Auditory Grouping Principles},
      • booktitle = {ICML 2020 Workshop on Self-supervision in Audio and Speech},
      • year = 2020,
      • month = jul,
      • url = {https://www.merl.com/publications/TR2020-111}
      • }
    •  Tsiligkaridis, A., Zhang, J., Taguchi, H., Nikovski, D.N., "Personalized Destination Prediction Using Transformers in a Contextless Data Setting", IEEE World Congress on Computational Intelligence (WCCI), July 2020.
      BibTeX TR2020-112 PDF
      • @inproceedings{Tsiligkaridis2020jul,
      • author = {Tsiligkaridis, Athanasios and Zhang, Jing and Taguchi, Hiroshi and Nikovski, Daniel N.},
      • title = {Personalized Destination Prediction Using Transformers in a Contextless Data Setting},
      • booktitle = {IEEE World Congress on Computational Intelligence (WCCI)},
      • year = 2020,
      • month = jul,
      • url = {https://www.merl.com/publications/TR2020-112}
      • }
    •  Chakrabarty, A., Jha, D., Buzzard, G.T., Wang, Y., Vamvoudakis, K., "Safe Approximate Dynamic Programming via Kernelized Lipschitz Estimation", IEEE Transactions on Neural Networks and Learning Systems, July 2020.
      BibTeX TR2020-108 PDF
      • @article{Chakrabarty2020jul2,
      • author = {Chakrabarty, Ankush and Jha, Devesh and Buzzard, Gregery T. and Wang, Yebin and Vamvoudakis, Kyriakos},
      • title = {Safe Approximate Dynamic Programming via Kernelized Lipschitz Estimation},
      • journal = {IEEE Transactions on Neural Networks and Learning Systems},
      • year = 2020,
      • month = jul,
      • url = {https://www.merl.com/publications/TR2020-108}
      • }
    •  Romeres, D., Liu, Y., Jha, D., Nikovski, D.N., "Understanding Multi-Modal Perception Using Behavioral Cloning for Peg-In-a-Hole Insertion Tasks", Robotics: Science and Systems, July 2020.
      BibTeX TR2020-110 PDF
      • @inproceedings{Romeres2020jul,
      • author = {Romeres, Diego and Liu, Yifang and Jha, Devesh and Nikovski, Daniel N.},
      • title = {Understanding Multi-Modal Perception Using Behavioral Cloning for Peg-In-a-Hole Insertion Tasks},
      • booktitle = {Robotics: Science and Systems},
      • year = 2020,
      • month = jul,
      • url = {https://www.merl.com/publications/TR2020-110}
      • }
    •  Menner, M., Berntorp, K., Di Cairano, S., "Inverse Learning for Data-driven Calibration of Model-based Statistical Path Planning", Transactions on Intelligent Vehicles, July 2020.
      BibTeX TR2020-106 PDF
      • @article{Menner2020jul,
      • author = {Menner, Marcel and Berntorp, Karl and Di Cairano, Stefano},
      • title = {Inverse Learning for Data-driven Calibration of Model-based Statistical Path Planning},
      • journal = {Transactions on Intelligent Vehicles},
      • year = 2020,
      • month = jul,
      • url = {https://www.merl.com/publications/TR2020-106}
      • }
    •  Berntorp, K., "Online Bayesian Tire-Friction Learning by Gaussian-Process State-Space Models", World Congress of the International Federation of Automatic Control (IFAC), July 2020.
      BibTeX TR2020-104 PDF
      • @inproceedings{Berntorp2020jul,
      • author = {Berntorp, Karl},
      • title = {Online Bayesian Tire-Friction Learning by Gaussian-Process State-Space Models},
      • booktitle = {World Congress of the International Federation of Automatic Control (IFAC)},
      • year = 2020,
      • month = jul,
      • url = {https://www.merl.com/publications/TR2020-104}
      • }
    •  Maske, H., Chu, T., Kalabic, U., "Control of traffic light timing using decentralized deep reinforcement learning", World Congress of the International Federation of Automatic Control (IFAC), July 2020.
      BibTeX TR2020-101 PDF
      • @inproceedings{Maske2020jul,
      • author = {Maske, Harshal and Chu, Tianshu and Kalabic, Uros},
      • title = {Control of traffic light timing using decentralized deep reinforcement learning},
      • booktitle = {World Congress of the International Federation of Automatic Control (IFAC)},
      • year = 2020,
      • month = jul,
      • url = {https://www.merl.com/publications/TR2020-101}
      • }
    See All Publications for Machine Learning
  • Videos

  • Software Downloads