- Date & Time: Tuesday, March 1, 2022; 1:00 PM EST
Speaker: David Harwath, The University of Texas at Austin
MERL Host: Chiori Hori
Research Areas: Artificial Intelligence, Machine Learning, Speech & Audio
Abstract - Humans learn spoken language and visual perception at an early age by being immersed in the world around them. Why can't computers do the same? In this talk, I will describe our ongoing work to develop methodologies for grounding continuous speech signals at the raw waveform level to natural image scenes. I will first present self-supervised models capable of discovering discrete, hierarchical structure (words and sub-word units) in the speech signal. Instead of conventional annotations, these models learn from correspondences between speech sounds and visual patterns such as objects and textures. Next, I will demonstrate how these discrete units can be used as a drop-in replacement for text transcriptions in an image captioning system, enabling us to directly synthesize spoken descriptions of images without the need for text as an intermediate representation. Finally, I will describe our latest work on Transformer-based models of visually-grounded speech. These models significantly outperform the prior state of the art on semantic speech-to-image retrieval tasks, and also learn representations that are useful for a multitude of other speech processing tasks.
-
- Date: January 24, 2022
Where: The TWIML AI Podcast
MERL Contact: Jonathan Le Roux
Research Areas: Artificial Intelligence, Machine Learning, Speech & Audio
Brief - MERL Speech & Audio Senior Team Leader Jonathan Le Roux was featured in an extended interview on the popular TWIML AI Podcast, presenting MERL's work towards solving the "cocktail party problem". Humans have the extraordinary ability to focus on particular sounds of interest within a complex acoustic scene, such as a cocktail party. MERL's Speech & Audio Team has been at the forefront of the field's effort to develop algorithms giving machines similar abilities. Jonathan talked with host Sam Charrington about the group's decade-long journey on this topic, from early pioneering work using deep learning for speech enhancement and speech separation, to recent works on weakly-supervised separation, hierarchical sound separation, as well as the separation of real-world soundtracks into speech, music, and sound effects (aka the "cocktail fork problem").
The TWIML AI podcast, formerly known as This Week in Machine Learning & AI, was created in 2016 and is followed by more than 10,000 subscribers on Youtube and Twitter. Jonathan's interview marks the 555th episode of the podcast.
-
- Date & Time: Tuesday, December 14, 2021; 1:00 PM EST
Speaker: Prof. Chris Fletcher, University of Waterloo
MERL Host: Ankush Chakrabarty
Research Areas: Dynamical Systems, Machine Learning, Multi-Physical Modeling
Abstract - Decision-making and adaptation to climate change requires quantitative projections of the physical climate system and an accurate understanding of the uncertainty in those projections. Earth system models (ESMs), which solve the Navier-Stokes equations on the sphere, are the only tool that climate scientists have to make projections forward into climate states that have not been observed in the historical data record. Yet, ESMs are incredibly complex and expensive codes and contain many poorly constrained physical parameters—for processes such as clouds and convection—that must be calibrated against observations. In this talk, I will describe research from my group that uses ensembles of ESM simulations to train statistical models that learn the behavior and sensitivities of the ESM. Once trained and validated the statistical models are essentially free to run, which allows climate modelling centers to make more efficient use of precious compute cycles. The aim is to improve the quality of future climate projections, by producing better calibrated ESMs, and to improve the quantification of the uncertainties, by better sampling the equifinality of climate states.
-
- Date & Time: December 9, 2021; 7pm EST
Where: virtual
MERL Contact: Toshiaki Koike-Akino
Research Areas: Communications, Machine Learning, Signal Processing
Brief - Toshiaki Koike-Akino (Signal Processing group, Network Intelligence Team) is giving an invited talk titled, `Evolution of Machine Learning for Photonic Research' for the Boston Photonic Chapter of the IEEE Photonic Society on December 9. The talk covers recent MERL research on machine learning for nonlinearity compensation and nanophotonic device design.
-
- Date & Time: Thursday, December 9, 2021; 1:00pm - 5:30pm EST
Location: Virtual Event
Speaker: Prof. Melanie Zeilinger, ETH
Research Areas: Applied Physics, Artificial Intelligence, Communications, Computational Sensing, Computer Vision, Control, Data Analytics, Dynamical Systems, Electric Systems, Electronic and Photonic Devices, Machine Learning, Multi-Physical Modeling, Optimization, Robotics, Signal Processing, Speech & Audio, Digital Video, Human-Computer Interaction, Information Security
Brief - MERL is excited to announce the second keynote speaker for our Virtual Open House 2021:
Prof. Melanie Zeilinger from ETH .
Our virtual open house will take place on December 9, 2021, 1:00pm - 5:30pm (EST).
Join us to learn more about who we are, what we do, and discuss our internship and employment opportunities. Prof. Zeilinger's talk is scheduled for 3:15pm - 3:45pm (EST).
Registration: https://mailchi.mp/merl/merlvoh2021
Keynote Title: Control Meets Learning - On Performance, Safety and User Interaction
Abstract: With increasing sensing and communication capabilities, physical systems today are becoming one of the largest generators of data, making learning a central component of autonomous control systems. While this paradigm shift offers tremendous opportunities to address new levels of system complexity, variability and user interaction, it also raises fundamental questions of learning in a closed-loop dynamical control system. In this talk, I will present some of our recent results showing how even safety-critical systems can leverage the potential of data. I will first briefly present concepts for using learning for automatic controller design and for a new safety framework that can equip any learning-based controller with safety guarantees. The second part will then discuss how expert and user information can be utilized to optimize system performance, where I will particularly highlight an approach developed together with MERL for personalizing the motion planning in autonomous driving to the individual driving style of a passenger.
-
- Date & Time: Thursday, December 9, 2021; 1:00pm - 5:30pm EST
Location: Virtual Event
Speaker: Prof. Ashok Veeraraghavan, Rice University
Research Areas: Applied Physics, Artificial Intelligence, Communications, Computational Sensing, Computer Vision, Control, Data Analytics, Dynamical Systems, Electric Systems, Electronic and Photonic Devices, Machine Learning, Multi-Physical Modeling, Optimization, Robotics, Signal Processing, Speech & Audio, Digital Video, Human-Computer Interaction, Information Security
Brief - MERL is excited to announce the first keynote speaker for our Virtual Open House 2021:
Prof. Ashok Veeraraghavan from Rice University.
Our virtual open house will take place on December 9, 2021, 1:00pm - 5:30pm (EST).
Join us to learn more about who we are, what we do, and discuss our internship and employment opportunities. Prof. Veeraraghavan's talk is scheduled for 1:15pm - 1:45pm (EST).
Registration: https://mailchi.mp/merl/merlvoh2021
Keynote Title: Computational Imaging: Beyond the limits imposed by lenses.
Abstract: The lens has long been a central element of cameras, since its early use in the mid-nineteenth century by Niepce, Talbot, and Daguerre. The role of the lens, from the Daguerrotype to modern digital cameras, is to refract light to achieve a one-to-one mapping between a point in the scene and a point on the sensor. This effect enables the sensor to compute a particular two-dimensional (2D) integral of the incident 4D light-field. We propose a radical departure from this practice and the many limitations it imposes. In the talk we focus on two inter-related research projects that attempt to go beyond lens-based imaging.
First, we discuss our lab’s recent efforts to build flat, extremely thin imaging devices by replacing the lens in a conventional camera with an amplitude mask and computational reconstruction algorithms. These lensless cameras, called FlatCams can be less than a millimeter in thickness and enable applications where size, weight, thickness or cost are the driving factors. Second, we discuss high-resolution, long-distance imaging using Fourier Ptychography, where the need for a large aperture aberration corrected lens is replaced by a camera array and associated phase retrieval algorithms resulting again in order of magnitude reductions in size, weight and cost. Finally, I will spend a few minutes discussing how the wholistic computational imaging approach can be used to create ultra-high-resolution wavefront sensors.
-
- 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 Processing
Brief - 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.
-
- Date & Time: Tuesday, November 16, 2021; 11:00 AM EST
Speaker: Thomas Schön, Uppsala University
MERL Host: Karl Berntorp
Research Areas: Dynamical Systems, Machine Learning
Abstract - While deep learning-based classification is generally addressed using standardized approaches, this is really not the case when it comes to the study of regression problems. There are currently several different approaches used for regression and there is still room for innovation. We have developed a general deep regression method with a clear probabilistic interpretation. The basic building block in our construction is an energy-based model of the conditional output density p(y|x), where we use a deep neural network to predict the un-normalized density from input-output pairs (x, y). Such a construction is also commonly referred to as an implicit representation. The resulting learning problem is challenging and we offer some insights on how to deal with it. We show good performance on several computer vision regression tasks, system identification problems and 3D object detection using laser data.
-
- Date & Time: Thursday, December 9, 2021; 100pm-5:30pm (EST)
Location: Virtual Event
Research Areas: Applied Physics, Artificial Intelligence, Communications, Computational Sensing, Computer Vision, Control, Data Analytics, Dynamical Systems, Electric Systems, Electronic and Photonic Devices, Machine Learning, Multi-Physical Modeling, Optimization, Robotics, Signal Processing, Speech & Audio, Digital Video, Human-Computer Interaction, Information Security
Brief - Mitsubishi Electric Research Laboratories cordially invites you to join our Virtual Open House, on December 9, 2021, 1:00pm - 5:30pm (EST).
The event will feature keynotes, live sessions, research area booths, and time for open interactions with our researchers. Join us to learn more about who we are, what we do, and discuss our internship and employment opportunities.
Registration: https://mailchi.mp/merl/merlvoh2021
-
- Date: December 10, 2021
Research Areas: Electronic and Photonic Devices, Machine Learning
Brief - MERL's Researcher Dr. Rui Ma is the keynote speaker for Electronic Design Innovation CON (EDICON2021) to be held in Shenzhen, China from Dec. 9-10, with a talk titled "Digitization and intelligence: unlocking the innovation of future radios". The conference brings together international researchers from academics, industry, and media distribution to share perspectives on the technology needed and being developed for the next generation of communication.
-
- Date & Time: Tuesday, November 2, 2021; 1:00 PM EST
Speaker: Dr. Hsiao-Yu (Fish) Tung, MIT BCS
Research Areas: Artificial Intelligence, Computer Vision, Machine Learning, Robotics
Abstract - Current state-of-the-art CNNs can localize and name objects in internet photos, yet, they miss the basic knowledge that a two-year-old toddler has possessed: objects persist over time despite changes in the observer’s viewpoint or during cross-object occlusions; objects have 3D extent; solid objects do not pass through each other. In this talk, I will introduce neural architectures that learn to parse video streams of a static scene into world-centric 3D feature maps by disentangling camera motion from scene appearance. I will show the proposed architectures learn object permanence, can imagine RGB views from novel viewpoints in truly novel scenes, can conduct basic spatial reasoning and planning, can infer affordability in sentences, and can learn geometry-aware 3D concepts that allow pose-aware object recognition to happen with weak/sparse labels. Our experiments suggest that the proposed architectures are essential for the models to generalize across objects and locations, and it overcomes many limitations of 2D CNNs. I will show how we can use the proposed 3D representations to build machine perception and physical understanding more close to humans.
-
- Date: October 21, 2021
Where: Université de Lorraine, France
MERL Contact: Ankush Chakrabarty
Research Areas: Artificial Intelligence, Control, Machine Learning, Multi-Physical Modeling, Optimization
Brief - Ankush Chakrabarty (RS, Multiphysical Systems Team) gave an invited talk on `Bayesian-Optimized Estimation and Control for Buildings and HVAC' at the Research Center for Automatic Control (CRAN) in the University of Lorraine in France. The talk presented recent MERL research on probabilistic machine learning for set-point optimization and calibration of digital twins for building energy systems.
-
- Date: October 18, 2021
Awarded to: Daniel Nikovski
MERL Contact: Daniel N. Nikovski
Research Areas: Artificial Intelligence, Machine Learning
Brief - 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.
-
- Date & Time: Tuesday, October 12, 2021; 1:00 PM EST
Speaker: Prof. Greg Ongie, Marquette University
MERL Host: Hassan Mansour
Research Areas: Computational Sensing, Machine Learning, Signal Processing
Abstract - Deep learning is emerging as powerful tool to solve challenging inverse problems in computational imaging, including basic image restoration tasks like denoising and deblurring, as well as image reconstruction problems in medical imaging. This talk will give an overview of the state-of-the-art supervised learning techniques in this area and discuss two recent innovations: deep equilibrium architectures, which allows one to train an effectively infinite-depth reconstruction network; and model adaptation methods, that allow one to adapt a pre-trained reconstruction network to changes in the imaging forward model at test time.
-
- Date & Time: Tuesday, September 28, 2021; 1:00 PM EST
Speaker: Dr. Ruohan Gao, Stanford University
MERL Host: Gordon Wichern
Research Areas: Computer Vision, Machine Learning, Speech & Audio
Abstract - While computer vision has made significant progress by "looking" — detecting objects, actions, or people based on their appearance — it often does not listen. Yet cognitive science tells us that perception develops by making use of all our senses without intensive supervision. Towards this goal, in this talk I will present my research on audio-visual learning — We disentangle object sounds from unlabeled video, use audio as an efficient preview for action recognition in untrimmed video, decode the monaural soundtrack into its binaural counterpart by injecting visual spatial information, and use echoes to interact with the environment for spatial image representation learning. Together, these are steps towards multimodal understanding of the visual world, where audio serves as both the semantic and spatial signals. In the end, I will also briefly talk about our latest work on multisensory learning for robotics.
-
- Date & Time: Tuesday, September 14, 2021; 1:00 PM EST
Speaker: Prof. David Bergman, University of Connecticut
MERL Host: Arvind Raghunathan
Research Areas: Data Analytics, Machine Learning, Optimization
Abstract - The integration of machine learning and optimization opens the door to new modeling paradigms that have already proven successful across a broad range of industries. Sports betting is a particularly exciting application area, where recent advances in both analytics and optimization can provide a lucrative edge. In this talk we will discuss three algorithmic sports betting games where combinations of machine learning and optimization have netted me significant winnings.
-
- Date: September 7, 2021
MERL Contact: Anoop Cherian
Research Areas: Artificial Intelligence, Computer Vision, Machine Learning
Brief - Anoop Cherian, a Principal Research Scientist in MERL's Computer Vision group, gave an invited virtual talk on "InSeGAN: An Unsupervised Approach to Identical Instance Segmentation" at the Visual Information Laboratory of University of Bristol, UK. The talk described a new approach to segmenting varied appearances of nearly identical 3D objects in depth images. More details of the talk can be found in the following paper https://arxiv.org/abs/2108.13865, which will be presented at the International Conference on Computer Vision (ICCV'21).
-
- Date: August 12, 2021
MERL Contact: Anthony Vetro
Research Areas: Artificial Intelligence, Computer Vision, Control, Dynamical Systems, Machine Learning, Optimization, Robotics
Brief - Anthony Vetro gave a keynote at the inaugural IEEE Conference on Autonomous Systems (ICAS), which was held virtually from August 11-13, 2021. The talk focused on challenges and recent progress in the area of robotic manipulation. The conference is sponsored by IEEE Signal Processing Society (SPS) through the SPS Autonomous Systems Initiative.
Abstract: Human-level manipulation continues to be beyond the capabilities of today’s robotic systems. Not only do current industrial robots require significant time to program a specific task, but they lack the flexibility to generalize to other tasks and be robust to changes in the environment. While collaborative robots help to reduce programming effort and improve the user interface, they still fall short on generalization and robustness. This talk will highlight recent advances in a number of key areas to improve the manipulation capabilities of autonomous robots, including methods to accurately model the dynamics of the robot and contact forces, sensors and signal processing algorithms to provide improved perception, optimization-based decision-making and control techniques, as well as new methods of interactivity to accelerate and enhance robot learning.
-
- Date: July 13, 2021
Where: Robotics: Science and Systems
MERL Contacts: Siddarth Jain; Devesh K. Jha; Diego Romeres
Research Areas: Artificial Intelligence, Machine Learning, Robotics
Brief - 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.
-
- Date: June 18, 2021
MERL Contact: Mouhacine Benosman
Research Areas: Electronic and Photonic Devices, Machine Learning, Signal Processing
Brief - 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.
-
- Date: April 15, 2021
MERL Contacts: Mouhacine Benosman; Koon Hoo Teo
Research Areas: Communications, Electronic and Photonic Devices, Machine Learning
Brief - The cover article in the April issue of Microwave Journal features MERL and MELCO's invited paper entitled "A New Frontier for Power Amplifiers Enabled by Machine Learning". Our recent research applying ML for optimizing operating conditions of advanced power amplifier designs is highlighted.
Since 1958, Microwave Journal has been the leading source for information about RF and Microwave technology, design techniques, news, events and educational information. Microwave Journal reaches 50,000 qualified readers monthly with a print magazine that has a global reach.
-
- Date: April 9, 2021
MERL Contact: Ankush Chakrabarty
Research Areas: Control, Machine Learning, Multi-Physical Modeling, Optimization
Brief - Ankush Chakrabarty, a Research Scientist at MERL's Multiphysical Systems (MS) Team, gave an invited talk on "Learning for Control and Estimation using Digital Twins" at the Department of Electrical and Computer Engineering Seminar Series organized at UIC. The talk proposed new learning-based control/estimation architectures that can utilize simulation data obtained from digital twins to add self-optimization and constraint-enforcement features to grey/black-box control systems.
-
- Date: April 7, 2021
Where: Online
MERL Contact: Devesh K. Jha
Research Areas: Artificial Intelligence, Machine Learning, Robotics
Brief - Devesh Jha, a Principal Research Scientist in MERL's Data Analytics group, gave an invited talk at the robotics seminar series at the University of Leeds. The talk presented some of the recent work done at MERL in the areas of robotic manipulation and robot learning.
-
- Date: February 15, 2021
Where: Virtual
MERL Contact: Diego Romeres
Research Areas: Artificial Intelligence, Machine Learning, Robotics
Brief - Diego Romeres, a Principal Research Scientist in MERL's Data Analytics group, gave the invited talk "Reinforcement Learning for Robotics" at the Autonomy Talks organized at ETH, Zurich. In the presentation, some directions to apply Model-based Reinforcement Learning algorithms to real-world applications are presented together with a novel MBRL algorithm called MC-PILCO. The link to the presentation is https://www.youtube.com/watch?v=wYgbgMa4j-s.
-
- Date & Time: Tuesday, February 16, 2021; 11:00-12:00
Speaker: Prof. Pere Gilabert, Universitat Politecnica de Catalunya, Barcelona, Spain
Research Areas: Communications, Electronic and Photonic Devices, Machine Learning, Signal Processing
Abstract - Digital predistortion (DPD) linearization is the most common and spread solution to cope with power amplifiers (PA) inherent linearity versus efficiency trade-off. The use of new radio 5G spectrally efficient signals with high peak-to-average power ratios (PAPR) occupying wider bandwidths only aggravates such compromise. When considering wide bandwidth signals, carrier aggregation or multi-band configurations in high efficient transmitter architectures, such as Doherty PAs, load-modulated balanced amplifiers, envelope tracking PAs or outphasing transmitters, the number of parameters required in the DPD model to compensate for both nonlinearities and memory effects can be unacceptably high. This has a negative impact in the DPD model extraction/adaptation, because it increases the computational complexity and drives to over-fitting and uncertainty.
This talk will discuss the use of machine learning techniques for DPD linearization. The use of artificial neural networks (ANNs) for adaptive DPD linearization and approaches to reduce the coefficients adaptation time will be discussed. In addition, an overview on several feature-extraction techniques used to reduce the number of parameters of the DPD linearization system as well as to ensure proper, well-conditioned estimation for related variables will be presented.
-