News & Events

125 Events and Talks were found.




  •  TALK   High-Dimensional Analysis of Stochastic Optimization Algorithms for Estimation and Learning
    Date & Time: Tuesday, December 13, 2016; Noon
    Speaker: Yue M. Lu, John A. Paulson School of Engineering and Applied Sciences, Harvard University
    MERL Host: Petros T. Boufounos
    Research Areas: Multimedia, Computational Sensing, Machine Learning
    Brief
    • In this talk, we will present a framework for analyzing, in the high-dimensional limit, the exact dynamics of several stochastic optimization algorithms that arise in signal and information processing. For concreteness, we consider two prototypical problems: sparse principal component analysis and regularized linear regression (e.g. LASSO). For each case, we show that the time-varying estimates given by the algorithms will converge weakly to a deterministic "limiting process" in the high-dimensional limit. Moreover, this limiting process can be characterized as the unique solution of a nonlinear PDE, and it provides exact information regarding the asymptotic performance of the algorithms. For example, performance metrics such as the MSE, the cosine similarity and the misclassification rate in sparse support recovery can all be obtained by examining the deterministic limiting process. A steady-state analysis of the nonlinear PDE also reveals interesting phase transition phenomena related to the performance of the algorithms. Although our analysis is asymptotic in nature, numerical simulations show that the theoretical predictions are accurate for moderate signal dimensions.
  •  
  •  TALK   Reduced basis methods and their application in data science and uncertainty quantification
    Date & Time: Monday, December 12, 2016; 12:00 PM
    Speaker: Yanlai Chen, Department of Mathematics at the University of Massachusetts Dartmouth
    MERL Host: Andrew Knyazev
    Research Areas: Algorithms, Advanced Control Systems, Dynamical Systems
    Brief
    • Models of reduced computational complexity is indispensable in scenarios where a large number of numerical solutions to a parametrized problem are desired in a fast/real-time fashion. These include simulation-based design, parameter optimization, optimal control, multi-model/scale analysis, uncertainty quantification. Thanks to an offline-online procedure and the recognition that the parameter-induced solution manifolds can be well approximated by finite-dimensional spaces, reduced basis method (RBM) and reduced collocation method (RCM) can improve efficiency by several orders of magnitudes. The accuracy of the RBM solution is maintained through a rigorous a posteriori error estimator whose efficient development is critical and involves fast eigensolves.

      In this talk, I will give a brief introduction of the RBM/RCM, and explain how they can be used for data compression, face recognition, and significantly delaying the curse of dimensionality for uncertainty quantification.
  •  
  •  TALK   Collaborative dictionary learning from big, distributed data
    Date & Time: Friday, December 2, 2016; 11:00 AM
    Speaker: Prof. Waheed Bajwa, Rutgers University
    MERL Host: Petros T. Boufounos
    Research Areas: Multimedia, Computational Sensing
    Brief
    • While distributed information processing has a rich history, relatively less attention has been paid to the problem of collaborative learning of nonlinear geometric structures underlying data distributed across sites that are connected to each other in an arbitrary topology. In this talk, we discuss this problem in the context of collaborative dictionary learning from big, distributed data. It is assumed that a number of geographically-distributed, interconnected sites have massive local data and they are interested in collaboratively learning a low-dimensional geometric structure underlying these data. In contrast to some of the previous works on subspace-based data representations, we focus on the geometric structure of a union of subspaces (UoS). In this regard, we propose a distributed algorithm, termed cloud K-SVD, for collaborative learning of a UoS structure underlying distributed data of interest. The goal of cloud K-SVD is to learn an overcomplete dictionary at each individual site such that every sample in the distributed data can be represented through a small number of atoms of the learned dictionary. Cloud K-SVD accomplishes this goal without requiring communication of individual data samples between different sites. In this talk, we also theoretically characterize deviations of the dictionaries learned at individual sites by cloud K-SVD from a centralized solution. Finally, we numerically illustrate the efficacy of cloud K-SVD in the context of supervised training of nonlinear classsifiers from distributed, labaled training data.
  •  
  •  EVENT   MERL organizes Workshop on End-to-End Speech and Audio Processing at NIPS 2016
    Date: Saturday, December 10, 2016
    MERL Contact: John R. Hershey
    Location: Centre Convencions Internacional Barcelona, Barcelona SPAIN
    Research Areas: Multimedia, Machine Learning, Speech & Audio
    Brief
    • MERL researcher John Hershey, is organizing a Workshop on End-to-End Speech and Audio Processing, on behalf of MERL's Speech and Audio team, and in collaboration with Philemon Brakel of the University of Montreal. The workshop focuses on recent advances to end-to-end deep learning methods to address alignment and structured prediction problems that naturally arise in speech and audio processing. The all day workshop takes place on Saturday, December 10th at NIPS 2016, in Barcelona, Spain.
  •  
  •  EVENT   2016 IEEE Workshop on Spoken Language Technology: Sponsored by MERL
    Date: Tuesday, December 13, 2016 - Friday, December 16, 2016
    MERL Contact: John R. Hershey
    Location: San Diego, California
    Research Areas: Multimedia, Speech & Audio
    Brief
    • The IEEE Workshop on Spoken Language Technology is a premier international showcase for advances in spoken language technology. The theme for 2016 is "machine learning: from signal to concepts," which reflects the current excitement about end-to-end learning in speech and language processing. This year, MERL is showing its support for SLT as one of its top sponsors, along with Amazon and Microsoft.
  •  
  •  EVENT   John Hershey to present tutorial at the 2016 IEEE SLT Workshop
    Date: Tuesday, December 13, 2016
    Speaker: John Hershey, MERL
    MERL Contacts: John R. Hershey; Jonathan Le Roux; Shinji Watanabe
    Location: 2016 IEEE Spoken Language Technology Workshop, San Diego, California
    Research Areas: Multimedia, Machine Learning, Speech & Audio
    Brief
    • MERL researcher John Hershey presents an invited tutorial at the 2016 IEEE Workshop on Spoken Language Technology, in San Diego, California. The topic, "developing novel deep neural network architectures from probabilistic models" stems from MERL work with collaborators Jonathan Le Roux and Shinji Watanabe, on a principled framework that seeks to improve our understanding of deep neural networks, and draws inspiration for new types of deep network from the arsenal of principles and tools developed over the years for conventional probabilistic models. The tutorial covers a range of parallel ideas in the literature that have formed a recent trend, as well as their application to speech and language.
  •  
  •  EVENT   MERL Open House
    Date & Time: Thursday, December 8, 2016; 4:00-7:00pm
    MERL Contacts: Elizabeth Phillips; Anthony Vetro
    Location: 201 Broadway, 8th Floor, Cambridge, MA
    Research Areas: Electronics & Communications, Multimedia, Data Analytics, Computer Vision, Mechatronics, Algorithms, Business Innovation
    Brief
    • Snacks, demos, science: On Thursday 12/8, Mitsubishi Electric Research Labs (MERL) will host an open house for graduate+ students interested in internships, post-docs, and research scientist positions. The event will be held from 4-7pm and will feature demos & short presentations in our main areas of research: algorithms, multimedia, electronics, communications, computer vision, speech processing, optimization, machine learning, data analytics, mechatronics, dynamics, control, and robotics. MERL is a high impact publication-oriented research lab with very extensive internship and university collaboration programs. Most internships lead to publication; many of our interns and staff have gone on to notable careers at MERL and in academia. Come mix with our researchers, see our state of the art technologies, and learn about our research opportunities. Dress code: casual, with resumes.

      Pre-registration for the event is strongly encouraged:
      https://www.eventbrite.com/e/merl-open-house-tickets-29408503626

      Current internship and employment openings:
      http://www.merl.com/internship/openings
      http://www.merl.com/employment/employment
  •  
  •  EVENT   MERL participating in Engineering Career Fair
    Date & Time: Wednesday, November 16, 2016; 3:30-6:30pm
    MERL Contacts: Elizabeth Phillips; Anthony Vetro
    Location: Sheraton Commander (16 Garden Street, Cambridge, MA)
    Research Areas: Electronics & Communications, Multimedia, Data Analytics, Computer Vision, Mechatronics, Algorithms, Business Innovation
    Brief
    • MERL will be participating in the Engineering Career Fair Collaborative, which is being held on November 16, 2016 at the Sheraton Commander in Cambridge from 3:30-6:30pm. Graduate students with an interest in learning about internship and other employment opportunities at MERL are invited to visit our booth. Staff members will be on hand to discuss current openings. We will also be showing some demonstrations of current research projects.

      Current internship and employment openings:
      http://www.merl.com/internship/openings
      http://www.merl.com/employment/employment
  •  
  •  EVENT   SANE 2016 - Speech and Audio in the Northeast
    Date: Friday, October 21, 2016
    MERL Contacts: John R. Hershey; Jonathan Le Roux; Shinji Watanabe
    Location: MIT, McGovern Institute for Brain Research, Cambridge, MA
    Research Areas: Multimedia, Speech & Audio
    Brief
    • SANE 2016, a one-day event gathering researchers and students in speech and audio from the Northeast of the American continent, will be held on Friday October 21, 2016 at MIT's Brain and Cognitive Sciences Department, at the McGovern Institute for Brain Research, in Cambridge, MA.

      It is a follow-up to SANE 2012 (Mitsubishi Electric Research Labs - MERL), SANE 2013 (Columbia University), SANE 2014 (MIT CSAIL), and SANE 2015 (Google NY). Since the first edition, the audience has steadily grown, gathering 140 researchers and students in 2015.

      SANE 2016 will feature invited talks by leading researchers: Juan P. Bello (NYU), William T. Freeman (MIT/Google), Nima Mesgarani (Columbia University), DAn Ellis (Google), Shinji Watanabe (MERL), Josh McDermott (MIT), and Jesse Engel (Google). It will also feature a lively poster session during lunch time, open to both students and researchers.

      SANE 2016 is organized by Jonathan Le Roux (MERL), Josh McDermott (MIT), Jim Glass (MIT), and John R. Hershey (MERL).
  •  
  •  TALK   Foundations of Green Communications
    Date & Time: Friday, September 23, 2016; 12:00 PM- 1:00 PM
    Speaker: Dr. Earl McCune, Eridan Communications
    MERL Host: Rui Ma
    Research Areas: Electronics & Communications, Power & RF, Wireless Communications & Signal Processing
    Brief
    • To maximize the operating energy efficiency of any wireless communication link requires a global optimization not only across the entire block diagram, but also including the selected signal modulation and aspects of the link operating protocol. Achieving this global optimization is first examined for the transmitter, receiver, and baseband circuitry. Then the important aspects of signal modulation necessary to access these circuit optimizations, with examples, are presented, followed by the correspondingly important protocol aspects needed. A metric called modulation-available energy efficiency (MAEE) compares proposed signals for compatibility with high energy efficiency objectives.
  •  
  •  TALK   Atomic-level modelling of materials with applications to semi-conductors.
    Date & Time: Wednesday, August 17, 2016; 1 PM
    Speaker: Gilles Zerah, Centre Francais en Calcul Atomique et Moleculaire-Ile-de-France (CFCAM-IdF)
    MERL Host: Andrew Knyazev
    Research Areas: Electronics & Communications, Algorithms, Optical Communications & Devices
    Brief
    • The first part of the talk is a high-level review of modern technologies for atomic-level modelling of materials. The second part discusses band gap calculations and MERL results for semi-conductors.
  •  
  •  EVENT   MERL Hosts 2nd Annual Women In Science Celebration
    Date & Time: Friday, July 22, 2016; 12:00 Noon
    MERL Contacts: Elizabeth Phillips; Jinyun Zhang
    Location: Cambridge Brewery
    Research Areas: Electronics & Communications, Multimedia, Data Analytics, Computer Vision, Mechatronics, Algorithms
    Brief
    • MERL hosted its 2nd Annual "Women In Science Celebration". MERL's current team of female interns discussed and celebrated the contributions they've made during their internships at MERL.
  •  
  •  TALK   A computational spectral graph theory tutorial
    Date & Time: Wednesday, July 13, 2016; 2:30 PM - 3:30
    Speaker: Richard Lehoucq, Sandia National Laboratories
    MERL Host: Andrew Knyazev
    Research Areas: Data Analytics, Computer Vision, Algorithms, Computational Photography, Digital Video, Machine Learning, Speech & Audio
    Brief
    • My presentation considers the research question of whether existing algorithms and software for the large-scale sparse eigenvalue problem can be applied to problems in spectral graph theory. I first provide an introduction to several problems involving spectral graph theory. I then provide a review of several different algorithms for the large-scale eigenvalue problem and briefly introduce the Anasazi package of eigensolvers.
  •  
  •  EVENT   MERL participates in SIAM Career fair
    Date & Time: Monday, July 11, 2016; 10 AM - 9:15 PM
    MERL Contacts: Matthew E. Brand; Piyush Grover; Joseph Katz; Andrew Knyazev; Arvind U. Raghunathan
    Location: Westin Boston Waterfront Pavilion, Boston, Massachusetts
    Research Areas: Data Analytics, Mechatronics, Algorithms
    Brief
    • MERL researchers participate in SIAM Job fair to showcase MERL's research and highlight employment and intern opportunities at MERL. The Career Fair emphasizes careers in business, industry, and government, and takes place during the SIAM Annual Meeting.

      The SIAM Applied Mathematics and Computational Science Career Fair is an informational and interactive event at which employers and prospective employees can discuss careers. It is a great opportunity for prospective employees to meet government and industry representatives and discuss what they are looking for and what each employer has to offer.
  •  
  •  TALK   Controlling the Grid Edge: Emerging Grid Operation Paradigms
    Date & Time: Thursday, July 7, 2016; 2:00 PM
    Speaker: Dr. Sonja Glavaski, Program Director, ARPA-E
    MERL Host: Arvind U. Raghunathan
    Research Areas: Data Analytics, Advanced Control Systems, Decision Optimization, Power & RF
    Brief
    • The evolution of the grid faces significant challenges if it is to integrate and accept more energy from renewable generation and other Distributed Energy Resources (DERs). To maintain grid's reliability and turn intermittent power sources into major contributors to the U.S. energy mix, we have to think about the grid differently and design it to be smarter and more flexible.

      ARPA-E is interested in disruptive technologies that enable increased integration of DERs by real-time adaptation while maintaining grid reliability and reducing cost for customers with smart technologies. The potential impact is significant, with projected annual energy savings of more than 3 quadrillion BTU and annual CO2 emissions reductions of more than 250 million metric tons.

      This talk will identify opportunities in developing next generation control technologies and grid operation paradigms that address these challenges and enable secure, stable, and reliable transmission and distribution of electrical power. Summary of newly announced ARPA-E NODES (Network Optimized Distributed Energy Systems) Program funding development of these technologies will be presented.
  •  
  •  EVENT   MERL celebrates 25 years of innovation
    Date: Thursday, June 2, 2016
    MERL Contacts: Elizabeth Phillips; Anthony Vetro
    Location: Norton's Woods Conference Center at American Academy of Arts & Sciences, Cambridge, MA
    Research Areas: Electronics & Communications, Multimedia, Data Analytics, Computer Vision, Mechatronics, Algorithms, Business Innovation
    Brief
    • MERL celebrated 25 years of innovation on Thursday, June 2 at the Norton's Woods Conference Center at the American Academy of Arts & Sciences in Cambridge, MA. The event was a great success, with inspiring keynote talks, insightful panel sessions, and an exciting research showcase of MERL's latest breakthroughs.

      Please visit the event page to view photos of each session, video presentations, as well as a commemorative booklet that highlights past and current research.
  •  
  •  TALK   Speech structure and its application to speech processing -- Relational, holistic and abstract representation of speech
    Date & Time: Friday, June 3, 2016; 1:30PM - 3:00PM
    Speaker: Nobuaki Minematsu and Daisuke Saito, The University of Tokyo
    MERL Host: Shinji Watanabe
    Research Areas: Multimedia, Speech & Audio
    Brief
    • Speech signals covey various kinds of information, which are grouped into two kinds, linguistic and extra-linguistic information. Many speech applications, however, focus on only a single aspect of speech. For example, speech recognizers try to extract only word identity from speech and speaker recognizers extract only speaker identity. Here, irrelevant features are often treated as hidden or latent by applying the probability theory to a large number of samples or the irrelevant features are normalized to have quasi-standard values. In speech analysis, however, phases are usually removed, not hidden or normalized, and pitch harmonics are also removed, not hidden or normalized. The resulting speech spectrum still contains both linguistic information and extra-linguistic information. Is there any good method to remove extra-linguistic information from the spectrum? In this talk, our answer to that question is introduced, called speech structure. Extra-linguistic variation can be modeled as feature space transformation and our speech structure is based on the transform-invariance of f-divergence. This proposal was inspired by findings in classical studies of structural phonology and recent studies of developmental psychology. Speech structure has been applied to accent clustering, speech recognition, and language identification. These applications are also explained in the talk.
  •  
  •  TALK   On computer simulation of multiscale processes in porous electrodes of Li-ion batteries
    Date & Time: Friday, May 13, 2016; 12:00 PM
    Speaker: Oleg Iliev, Fraunhofer Institute for Industrial Mathematics, ITWM
    MERL Host: Andrew Knyazev
    Research Areas: Algorithms, Computer Vision, Mechatronics, Dynamical Systems
    Brief
    • Li-ion batteries are widely used in automotive industry, in electronic devices, etc. In this talk we will discuss challenges related to the multiscale nature of batteries, mainly the understanding of processes in the porous electrodes at pore scale and at macroscale. A software tool for simulation of isothermal and non-isothermal electrochemical processes in porous electrodes will be presented. The pore scale simulations are done on 3D images of porous electrodes, or on computer generated 3D microstructures, which have the same characterization as real porous electrodes. Finite Volume and Finite Element algorithms for the highly nonlinear problems describing processes at pore level will be shortly presented. Model order reduction, MOR, empirical interpolation method, EIM-MOR algorithms for acceleration of the computations will be discussed, as well as the reduced basis method for studying parameters dependent problems. Next, homogenization of the equations describing the electrochemical processes at the pore scale will be presented, and the results will be compared to the engineering approach based on Newman's 1D+1D model. Simulations at battery cell level will also be addressed. Finally, the challenges in modeling and simulation of degradation processes in the battery will be discussed and our first simulation results in this area will be presented.

      This is joint work with A.Latz (DLR), M.Taralov, V.Taralova, J.Zausch, S.Zhang from Fraunhofer ITWM, Y.Maday from LJLL, Paris 6 and Y.Efendiev from Texas A&M.
  •  
  •  EVENT   John Hershey Invited to Speak at Deep Learning Summit 2016 in Boston
    Date: Thursday, May 12, 2016 - Friday, May 13, 2016
    MERL Contact: John R. Hershey
    Location: Deep Learning Summit, Boston, MA
    Research Areas: Multimedia, Speech & Audio
    Brief
    • MERL Speech and Audio Senior Team Leader John Hershey is among a set of high-profile researchers invited to speak at the Deep Learning Summit 2016 in Boston on May 12-13, 2016. John will present the team's groundbreaking work on general sound separation using a novel deep learning framework called Deep Clustering. For the first time, an artificial intelligence is able to crack the half-century-old "cocktail party problem", that is, to isolate the speech of a single person from a mixture of multiple unknown speakers, as humans do when having a conversation in a loud crowd.
  •  
  •  TALK   Advanced Recurrent Neural Networks for Automatic Speech Recognition
    Date & Time: Friday, April 29, 2016; 12:00 PM - 1:00 PM
    Speaker: Yu Zhang, MIT
    MERL Host: Shinji Watanabe
    Research Areas: Multimedia, Speech & Audio
    Brief
    • A recurrent neural network (RNN) is a class of neural network models where connections between its neurons form a directed cycle. This creates an internal state of the network which allows it to exhibit dynamic temporal behavior. Recently the RNN-based acoustic models greatly improved automatic speech recognition (ASR) accuracy on many tasks, such as an advanced version of the RNN, which exploits a structure called long-short-term memory (LSTM). However, ASR performance with distant microphones, low resources, noisy, reverberant conditions, and on multi-talker speech are still far from satisfactory as compared to humans. To address these issues, we develop new strucute of RNNs inspired by two principles: (1) the structure follows the intuition of human speech recognition; (2) the structure is easy to optimize. The talk will go beyond basic RNNs, introduce prediction-adaptation-correction RNNs (PAC-RNNs) and highway LSTMs (HLSTMs). It studies both uni-directional and bi-direcitonal RNNs and discriminative training also applied on top the RNNs. For efficient training of such RNNs, the talk will describe two algorithms for learning their parameters in some detail: (1) Latency-Controlled bi-directional model training; and (2) Two pass forward computation for sequence training. Finally, this talk will analyze the advantages and disadvantages of different variants and propose future directions.
  •