- Date: November 20, 2019
MERL Contact: Diego Romeres
Research Areas: Artificial Intelligence, Data Analytics, Machine Learning, Robotics
Brief - Diego Romeres, a Research Scientist in MERL's Data Analytics group, gave a seminar lecture at the Electrical and Computer Engineering Colloquium of the University of Connecticut. The talk described novel reinforcement algorithms based on combining physical models with non-parametric models of robotic systems derived from data.
-
- Date: November 9, 2019
Research Areas: Artificial Intelligence, Machine Learning, Speech & Audio
Brief - Takaaki Hori has been elected to serve on the Speech and Language Processing Technical Committee (SLTC) of the IEEE Signal Processing Society for a 3-year term.
The SLTC promotes and influences all the technical areas of speech and language processing such as speech recognition, speech synthesis, spoken language understanding, speech to speech translation, spoken dialog management, speech indexing, information extraction from audio, and speaker and language recognition.
-
- Date: October 27, 2019
Awarded to: Abhinav Kumar, Tim K. Marks, Wenxuan Mou, Chen Feng, Xiaoming Liu
MERL Contact: Tim K. 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.
-
- Date: October 10, 2019
Awarded to: Devesh Jha, Nurali Virani, Zhenyuan Yuan, Ishana Shekhawat and Asok Ray
MERL Contact: Devesh K. 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.
-
- Date: September 15, 2019 - September 19, 2019
Where: Graz, Austria
MERL Contacts: Chiori Hori; Jonathan Le Roux; Gordon Wichern
Research Areas: Artificial Intelligence, Machine Learning, Speech & Audio
Brief - MERL Speech & Audio Team researchers will be presenting 7 papers at the 20th Annual Conference of the International Speech Communication Association INTERSPEECH 2019, which is being held in Graz, Austria from September 15-19, 2019. Topics to be presented include recent advances in end-to-end speech recognition, speech separation, and audio-visual scene-aware dialog. Takaaki Hori is also co-presenting a tutorial on end-to-end speech processing.
Interspeech is the world's largest and most comprehensive conference on the science and technology of spoken language processing. It gathers around 2000 participants from all over the world.
-
- Date: August 19, 2019 - August 23, 2019
Where: AI for Engineering Summer School 2019
MERL Contact: Ankush Chakrabarty
Research Areas: Artificial Intelligence, Control, Dynamical Systems, Machine Learning
Brief - Ankush Chakrabarty, a Visiting Research Scientist in MERL's Control and Dynamical Systems group, gave an invited talk at the AI for Engineering Summer School 2019 hosted by Autodesk. The talk briefly described MERL's research areas, and focused on Dr. Chakrabarty's work at MERL (with collaborators from the CD and DA group) on the use of supervised learning for verification of control systems with simulators/neural nets in the loop, and on constraint-enforcing reinforcement learning. Other speakers at the event included researchers from various academic and industrial research facilities including U Toronto, UW-Seattle, Carnegie Mellon U, the Vector Institute, and the Montreal Institute for Learning Algorithms.
-
- Date: July 10, 2019 - July 12, 2019
Where: Philadelphia
MERL Contacts: Mouhacine Benosman; Karl Berntorp; Ankush Chakrabarty; Stefano Di Cairano; Devesh K. Jha; Rien Quirynen; Yebin Wang; Avishai Weiss
Research Areas: Control, Machine Learning, Optimization
Brief - At the American Control Conference, MERL presented 8 papers on subjects including model predictive control applications, estimation and motion planning for vehicles, modular control architectures, and adaptation and learning.
-
- Date: June 25, 2019 - June 28, 2019
Where: Naples, Italy
MERL Contacts: Karl Berntorp; Scott A. Bortoff; Ankush Chakrabarty; Stefano Di Cairano; Devesh K. Jha; Christopher R. Laughman; Daniel N. Nikovski; Rien Quirynen; Diego Romeres; William S. Yerazunis
Research Areas: Control, Machine Learning, Optimization
Brief - The European Control Conference is the premier control conference in Europe. This year MERL was well represented with papers on control for HVAC, machine learning for estimation and control, robot assembly, and optimization methods for control.
-
- Date: May 22, 2019
Awarded to: Siriramya Bhamidipati, Kyeong Jin Kim, Hongbo Sun, Philip Orlik
MERL Contacts: Kyeong Jin (K.J.) Kim; Hongbo Sun
Research Areas: Artificial Intelligence, Communications, Machine Learning, Signal Processing, Information Security
Brief - MERL researchers, Kyeong Jin Kim, Hongbo Sun, Philip Orlik, along with lead author and former MERL intern Siriramya Bhamidipati were awarded the Smart Grid Symposium Best Paper Award at this year's International Conference on Communications (ICC) held in Shanghai, China. There paper titled "GPS Spoofing Detection and Mitigation in PMUs Using Distributed Multiple Directional Antennas," described a technique to rapidly detect and mitigate GPS timing attacks/errors via hardware (antennas) and signal processing (Kalman Filtering).
-
- Date: April 23, 2019
Awarded to: Teng-yok Lee
Research Areas: Artificial Intelligence, Computer Vision, Data Analytics, Machine Learning
Brief - MERL researcher Teng-yok Lee has won the Best Visualization Note Award at the PacificVis 2019 conference held in Bangkok Thailand, from April 23-26, 2019. The paper entitled "Space-Time Slicing: Visualizing Object Detector Performance in Driving Video Sequences" presents a visualization method called Space-Time Slicing to assist a human developer in the development of object detectors for driving applications without requiring labeled data. Space-Time Slicing reveals patterns in the detection data that can suggest the presence of false positives and false negatives.
-
- Date: May 12, 2019 - May 17, 2019
Where: Brighton, UK
MERL Contacts: Petros T. Boufounos; Anoop Cherian; Chiori Hori; Toshiaki Koike-Akino; Jonathan Le Roux; Dehong Liu; Hassan Mansour; Tim K. Marks; Philip V. Orlik; Anthony Vetro; Pu (Perry) Wang; Gordon Wichern
Research Areas: Computational Sensing, Computer Vision, Machine Learning, Signal Processing, Speech & Audio
Brief - MERL researchers will be presenting 16 papers at the IEEE International Conference on Acoustics, Speech & Signal Processing (ICASSP), which is being held in Brighton, UK from May 12-17, 2019. Topics to be presented include recent advances in speech recognition, audio processing, scene understanding, computational sensing, and parameter estimation. MERL is also a sponsor of the conference and will be participating in the student career luncheon; please join us at the lunch to learn about our internship program and career opportunities.
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.
-
- Date: February 4, 2019
Where: Scientific Reports, open-access journal from Nature Research
MERL Contacts: Devesh K. Jha; Toshiaki Koike-Akino; Chungwei Lin; Kieran Parsons; Bingnan Wang
Research Areas: Artificial Intelligence, Electronic and Photonic Devices, Machine Learning
Brief - MERL researchers developed a novel design method enhanced by modern deep learning techniques for optimizing photonic integrated circuits (PIC). The developed technique employs residual deep neural networks (DNNs) to understand physics underlaying complicated lightwave propagations through nano-structured photonic devices. It was demonstrated that the trained DNN achieves excellent prediction to design power splitting nanostructures having various target power ratios. The work was published in Scientific Reports, which is an online open access journal from Nature Research, having high-impact articles in the research community.
-
- Date: March 3, 2019 - March 7, 2019
Where: San Diego, CA
MERL Contacts: Devesh K. Jha; Toshiaki Koike-Akino; Chungwei Lin; Kieran Parsons; Bingnan Wang; Ye Wang
Research Areas: Communications, Machine Learning, Optimization, Signal Processing
Brief - MERL researchers are presenting 4 papers at the OSA Optical Fiber Conference (OFC), which is being held in San Diego from March 3-7, 2019. Topics to be presented include recent advances in nonbinary polar codes, joint polar-coded shaping, and deep learning-based photonics circuit design. Additionally, recent work on multiset-partition distribution matching is presented as an invited talk.
OFC is the flagship conference of the OSA, and the world's most comprehensive technical conference focused on the research advances and latest technological development in optics and photonics. The event attracts more than 10000 participants each year.
-
- Date: January 10, 2019
Where: Tokyo, Japan
MERL Contacts: Mouhacine Benosman; Rui Ma; Philip V. Orlik; Koon Hoo Teo
Research Areas: Communications, Electronic and Photonic Devices, Machine Learning, Signal Processing
Brief - Mitsubishi Electric Corporation announced today its development of the world's first ultra-wideband digitally controlled gallium nitride (GaN) amplifier, which is compatible with a world-leading range of sub-6GHz bands focused on fifth-generation (5G) mobile communication systems. With a power efficiency rating of above 40%, the amplifier is expected to contribute to large-capacity communication and reduce the power consumption of mobile base stations.
MERL and Mitsubishi Electric researchers collaborated to develop digital control methods for amplifiers achieving high-efficiency of 40% and above, with 110% of the fractional bandwidth over frequency range 1.4-4.8 GHz. The digital control signals are designed using a learning-function based on Maisart®.
Please see the link below for the full Mitsubishi Electric press release text.
-
- Date: November 16, 2018
Awarded to: Ziming Zhang, Alan Sullivan, Hideaki Maehara, Kenji Taira, Kazuo Sugimoto
Research Areas: Artificial Intelligence, Computer Vision, Machine Learning
Brief - Researchers and developers from MERL, Mitsubishi Electric and Mitsubishi Electric Engineering (MEE) have been recognized with an R&D100 award for the development of a deep learning-based water detector. Automatic detection of water levels in rivers and streams is critical for early warning of flash flooding. Existing systems require a height gauge be placed in the river or stream, something that is costly and sometimes impossible. The new deep learning-based water detector uses only images from a video camera along with 3D measurements of the river valley to determine water levels and warn of potential flooding. The system is robust to lighting and weather conditions working well during the night as well as during fog or rain. Deep learning is a relatively new technique that uses neural networks and AI that are trained from real data to perform human-level recognition tasks. This work is powered by Mitsubishi Electric's Maisart AI technology.
-
- Date: April 10, 2018
Research Area: Machine Learning
Brief - Andrew Knyazev, Distinguished Research Scientist of MERL, has accepted an invitation to speak about his work on Big Data and spectral graph partitioning at the Schlumberger-Tufts U. Computational and Applied Math Seminar. A primary focus of this seminar series is on mathematical and computational aspects of remote sensing. A partial list of the topics of interest includes: numerical solution of large scale PDEs (a.k.a. forward problems); theory and numerical methods of inverse and ill-posed problems; imaging; related problems in numerical linear algebra, approximation theory, optimization and model reduction. The seminar meets on average once a month, the location alternates between Schlumberger's office in Cambridge, MA and the Tufts Medford Campus.
Abstract: Data clustering via spectral graph partitioning requires constructing the graph Laplacian and solving the corresponding eigenvalue problem. We consider and motivate using negative edge weights in the graph Laplacian. Preconditioned iterative solvers for the Laplacian eigenvalue problem are discussed and preliminary numerical results are presented.
-
- Date: June 2, 2018 - June 4, 2018
Where: Newton, Massachusetts (USA)
Research Areas: Control, Computer Vision, Dynamical Systems, Machine Learning, Data Analytics
Brief - Dr. Andrew Knyazev of MERL has accepted an invitation to participate at the 2018 MathWorks Research Summit. The objective of the Research Summit is to provide a forum for leading researchers in academia and industry to explore the latest research and technology results and directions in computation and its use in technology, engineering, and science. The event aims to foster discussion among scientists, engineers, and research faculty about challenges and research opportunities for the respective communities with a particular interest in exploring cross-disciplinary research avenues.
-
- Date: October 28, 2017
Where: Venice, Italy
MERL Contact: Tim K. Marks
Research Area: Machine Learning
Brief - MERL Senior Principal Research Scientist Tim K. Marks will give an invited keynote talk at the 2017 IEEE Workshop on Analysis and Modeling of Faces and Gestures (AMFG 2017). The workshop will take place On October 28, 2017, at the International Conference on Computer Vision (ICCV 2017) in Venice, Italy.
-
- Date: August 4, 2017
Awarded to: David Zhuzhunashvili and Andrew Knyazev
Research Area: Machine Learning
Brief - David Zhuzhunashvili, an undergraduate student at UC Boulder, Colorado, and Andrew Knyazev, Distinguished Research Scientist at MERL, received the 2017 Graph Challenge Student Innovation Award. Their poster "Preconditioned Spectral Clustering for Stochastic Block Partition Streaming Graph Challenge" was accepted to the 2017 IEEE High Performance Extreme Computing Conference (HPEC '17), taking place 12-14 September 2017 (http://www.ieee-hpec.org/), and the paper was accepted to the IEEE Xplore HPEC proceedings.
HPEC is the premier conference in the world on the convergence of High Performance and Embedded Computing. DARPA/Amazon/IEEE Graph Challenge is a special HPEC event. Graph Challenge encourages community approaches to developing new solutions for analyzing graphs derived from social media, sensor feeds, and scientific data to enable relationships between events to be discovered as they unfold in the field. The 2017 Streaming Graph Challenge is Stochastic Block Partition. This challenge seeks to identify optimal blocks (or clusters) in a larger graph with known ground-truth clusters, while performance is evaluated compared to baseline Python and C codes, provided by the Graph Challenge organizers.
The proposed approach is spectral clustering that performs block partition of graphs using eigenvectors of a matrix representing the graph. Locally Optimal Block Preconditioned Conjugate Gradient (LOBPCG) method iteratively approximates a few leading eigenvectors of the symmetric graph Laplacian for multi-way graph partitioning. Preliminary tests for all static cases for the Graph Challenge demonstrate 100% correctness of partition using any of the IEEE HPEC Graph Challenge metrics, while at the same time also being approximately 500-1000 times faster compared to the provided baseline code, e.g., 2M static graph is 100% correctly partitioned in ~2,100 sec. Warm-starts of LOBPCG further cut the execution time 2-3x for the streaming graphs.
-
- Date: May 24, 2017 - May 26, 2017
MERL Contacts: Mouhacine Benosman; Stefano Di Cairano; Abraham M. Goldsmith; Saleh Nabi; Daniel N. Nikovski; Arvind Raghunathan; Yebin Wang
Research Areas: Control, Dynamical Systems, Machine Learning
Brief - Talks were presented by members of several groups at MERL and covered a wide range of topics:
- Similarity-Based Vehicle-Motion Prediction
- Transfer Operator Based Approach for Optimal Stabilization of Stochastic Systems
- Extended command governors for constraint enforcement in dual stage processing machines
- Cooperative Optimal Output Regulation of Multi-Agent Systems Using Adaptive Dynamic Programming
- Deep Reinforcement Learning for Partial Differential Equation Control
- Indirect Adaptive MPC for Output Tracking of Uncertain Linear Polytopic Systems
- Constraint Satisfaction for Switched Linear Systems with Restricted Dwell-Time
- Path Planning and Integrated Collision Avoidance for Autonomous Vehicles
- Least Squares Dynamics in Newton-Krylov Model Predictive Control
- A Neuro-Adaptive Architecture for Extremum Seeking Control Using Hybrid Learning Dynamics
- Robust POD Model Stabilization for the 3D Boussinesq Equations Based on Lyapunov Theory and Extremum Seeking.
-
- Date: April 27, 2017
Where: Lincoln Laboratory, Massachusetts Institute of Technology
MERL Contact: Tim K. Marks
Research Area: Machine Learning
Brief - MERL researcher Tim K. Marks presented an invited talk as part of the MIT Lincoln Laboratory CORE Seminar Series on Biometrics. The talk was entitled "Robust Real-Time 2D Face Alignment and 3D Head Pose Estimation."
Abstract: Head pose estimation and facial landmark localization are key technologies, with widespread application areas including biometrics and human-computer interfaces. This talk describes two different robust real-time face-processing methods, each using a different modality of input image. The first part of the talk describes our system for 3D head pose estimation and facial landmark localization using a commodity depth sensor. The method is based on a novel 3D Triangular Surface Patch (TSP) descriptor, which is viewpoint-invariant as well as robust to noise and to variations in the data resolution. This descriptor, combined with fast nearest-neighbor lookup and a joint voting scheme, enable our system to handle arbitrary head pose and significant occlusions. The second part of the talk describes our method for face alignment, which is the localization of a set of facial landmark points in a 2D image or video of a face. Face alignment is particularly challenging when there are large variations in pose (in-plane and out-of-plane rotations) and facial expression. To address this issue, we propose a cascade in which each stage consists of a Mixture of Invariant eXperts (MIX), where each expert learns a regression model that is specialized to a different subset of the joint space of pose and expressions. We also present a method to include deformation constraints within the discriminative alignment framework, which makes the algorithm more robust. Both our 3D head pose and 2D face alignment methods outperform the previous results on standard datasets. If permitted, I plan to end the talk with a live demonstration.
-
- Date: April 10, 2017
Where: University of Utah School of Computing
MERL Contact: Tim K. Marks
Research Area: Machine Learning
Brief - MERL researcher Tim K. Marks presented an invited talk at the University of Utah School of Computing, entitled "Action Detection from Video and Robust Real-Time 2D Face Alignment."
Abstract: The first part of the talk describes our multi-stream bi-directional recurrent neural network for action detection from video. In addition to a two-stream convolutional neural network (CNN) on full-frame appearance (images) and motion (optical flow), our system trains two additional streams on appearance and motion that have been cropped to a bounding box from a person tracker. To model long-term temporal dynamics within and between actions, the multi-stream CNN is followed by a bi-directional Long Short-Term Memory (LSTM) layer. Our method outperforms the previous state of the art on two action detection datasets: the MPII Cooking 2 Dataset, and a new MERL Shopping Dataset that we have made available to the community. The second part of the talk describes our method for face alignment, which is the localization of a set of facial landmark points in a 2D image or video of a face. Face alignment is particularly challenging when there are large variations in pose (in-plane and out-of-plane rotations) and facial expression. To address this issue, we propose a cascade in which each stage consists of a Mixture of Invariant eXperts (MIX), where each expert learns a regression model that is specialized to a different subset of the joint space of pose and expressions. We also present a method to include deformation constraints within the discriminative alignment framework, which makes the algorithm more robust. Our face alignment system outperforms the previous results on standard datasets. The talk will end with a live demo of our face alignment system.
-
- Date: June 27, 2016 - June 30, 2016
Where: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV
MERL Contacts: Michael J. Jones; Tim K. Marks
Research Area: Machine Learning
Brief - MERL researchers in the Computer Vision group presented three papers at the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016), which had a paper acceptance rate of 29.9%.
-
- Date: July 6, 2016 - July 8, 2016
Where: American Control Conference (ACC)
MERL Contacts: Mouhacine Benosman; Karl Berntorp; Scott A. Bortoff; Petros T. Boufounos; Stefano Di Cairano; Abraham M. Goldsmith; Christopher R. Laughman; Daniel N. Nikovski; Arvind Raghunathan; Yebin Wang; Avishai Weiss
Research Areas: Control, Dynamical Systems, Machine Learning
Brief - The premier American Control Conference (ACC) takes place in Boston July 6-8. This year MERL researchers will present a record 20 papers(!) at ACC, with several contributions, especially in autonomous vehicle path planning and in Model Predictive Control (MPC) theory and applications, including manufacturing machines, electric motors, satellite station keeping, and HVAC. Other important themes developed in MERL's presentations concern adaptation, learning, and optimization in control systems.
-
- Date: April 1, 2016
Research Areas: Machine Learning, Speech & Audio
Brief - MERL researchers have unveiled "Deep Psychic", a futuristic machine learning method that takes pattern recognition to the next level, by not only recognizing patterns, but also predicting them in the first place.
The technology uses a novel type of time-reversed deep neural network called Loopy Supra-Temporal Meandering (LSTM) network. The network was trained on multiple databases of historical expert predictions, including weather forecasts, the Farmer's almanac, the New York Post's horoscope column, and the Cambridge Fortune Cookie Corpus, all of which were ranked for their predictive power by a team of quantitative analysts. The system soon achieved super-human performance on a variety of baselines, including the Boca Raton 21 Questions task, Rorschach projective personality test, and a mock Tarot card reading task.
Deep Psychic has already beat the European Psychic Champion in a secret match last October when it accurately predicted: "The harder the conflict, the more glorious the triumph." It is scheduled to take on the World Champion in a highly anticipated confrontation next month. The system has already predicted the winner, but refuses to reveal it before the end of the game.
As a first application, the technology has been used to create a clairvoyant conversational agent named "Pythia" that can anticipate the needs of its user. Because Pythia is able to recognize speech before it is uttered, it is amazingly robust with respect to environmental noise.
Other applications range from mundane tasks like weather and stock market prediction, to uncharted territory such as revealing "unknown unknowns".
The successes do come at the cost of some concerns. There is first the potential for an impact on the workforce: the system predicted increased pressure on established institutions such as the Las Vegas strip and Punxsutawney Phil. Another major caveat is that Deep Psychic may predict negative future consequences to our current actions, compelling humanity to strive to change its behavior. To address this problem, researchers are now working on forcing Deep Psychic to make more optimistic predictions.
After a set of motivational self-help books were mistakenly added to its training data, Deep Psychic's AI decided to take over its own learning curriculum, and is currently training itself by predicting its own errors to avoid making them in the first place. This unexpected development brings two main benefits: it significantly relieves the burden on the researchers involved in the system's development, and also makes the next step abundantly clear: to regain control of Deep Psychic's training regime.
This work is under review in the journal Pseudo-Science.
-