- Date: December 14, 2015 - December 16, 2015
Where: Las Vegas, NV, USA
Research Area: Machine Learning
Brief - MERL researcher, Oncel Tuzel, gave a keynote talk at 2016 International Symposium on Visual Computing in Las Vegas, Dec. 16, 2015. The talk was titled: "Machine vision for robotic bin-picking: Sensors and algorithms" and reviewed MERL's research in the application of 2D and 3D sensing and machine learning to the problem of general pose estimation.
The talk abstract was: For over four years, at MERL, we have worked on the robot "bin-picking" problem: using a 2D or 3D camera to look into a bin of parts and determine the pose, 3D rotation and translation, of a good candidate to pick up. We have solved the problem several different ways with several different sensors. I will briefly describe the sensors and the algorithms. In the first half of the talk, I will describe the Multi-Flash camera, a 2D camera with 8 flashes, and explain how this inexpensive camera design is used to extract robust geometric features, depth edges and specular edges, from the parts in a cluttered bin. I will present two pose estimation algorithms, (1) Fast directional chamfer matching--a sub-linear time line matching algorithm and (2) specular line reconstruction, for fast and robust pose estimation of parts with different surface characteristics. In the second half of the talk, I will present a voting-based pose estimation algorithm applicable to 3D sensors. We represent three-dimensional objects using a set of oriented point pair features: surface points with normals and boundary points with directions. I will describe a max-margin learning framework to identify discriminative features on the surface of the objects. The algorithm selects and ranks features according to their importance for the specified task which leads to improved accuracy and reduced computational cost.
-
- Date: December 15, 2015
Where: 2015 IEEE Global Conference on Signal and Information Processing (GlobalSIP)
MERL Contact: Hassan Mansour
Research Area: Machine Learning
Brief - MERL researcher Andrew Knyazev gave 3 talks at the 2015 IEEE Global Conference on Signal and Information Processing (GlobalSIP). The papers were published in IEEE conference proceedings.
-
- Date: October 6, 2015
Where: IFAC workshop on control applications of optimization 2015
Research Area: Control
Brief - MERL researchers Andrew Knyazev and Alexander Malyshev gave two talks at the IFAC workshop on control applications of optimization, 2015. The papers were published by Elsevier B.V. in the conference proceedings.
-
- Date: Thursday, October 22, 2015
Location: Google, New York City, NY
MERL Contact: Jonathan Le Roux
Research Area: Speech & Audio
Brief - SANE 2015, a one-day event gathering researchers and students in speech and audio from the Northeast of the American continent, will be held on Thursday October 22, 2015 at Google, in New York City, NY.
It is a follow-up to SANE 2012, held at Mitsubishi Electric Research Labs (MERL), SANE 2013, held at Columbia University, and SANE 2014, held at MIT, which each gathered 70 to 90 researchers and students.
SANE 2015 will feature invited talks by leading researchers from the Northeast, as well as from the international community: Rohit Prasad (Amazon), Michael Mandel (Brooklyn College, CUNY), Ron Weiss (Google), John Hershey (MERL), Pablo Sprechmann (NYU), Tuomas Virtanen (Tampere University of Technology), and Paris Smaragdis (UIUC). It will also feature a lively poster session during lunch time, open to both students and researchers.
SANE 2015 is organized by Jonathan Le Roux (MERL), Hank Liao (Google), Andrew Senior (Google), and John R. Hershey (MERL).
-
- Date: September 18, 2015
Where: IEEE International Workshop on Machine Learning for Signal Processing (MLSP) 2015
Research Area: Machine Learning
Brief - MERL researchers A. Knyazev and A. Malyshev gave a talk at the IEEE International Workshop on Machine Learning for Signal Processing (MLSP) 2015. The paper was published at the IEEE Xplore conference proceedings.
-
- Date: July 13, 2015
Where: SIAM Conference on Control and Its Applications 2015
Research Area: Control
Brief - MERL and Mitsubishi Electric researchers presented talks at the SIAM Conference on Control and Its Applications 2015. The papers were published by SIAM in the conference proceedings.
-
- Date: June 1, 2015
Where: International Conference on Computational Science (ICCS) Brief - Andrew Knyazev gave a talk at the International Conference on Computational Science (ICCS), 2015 on Nonsymmetric preconditioning for conjugate gradient and steepest descent methods. The paper was published by Elsevier B.V. in the conference proceedings.
-
- Date: April 28, 2015
Brief - MERL researcher and speech team leader, John Hershey, gave a talk at MIT entitled, "Deep Unfolding: Deriving Novel Deep Network Architectures from Model-based Inference Methods" on April 28, 2015.
Abstract: Model-based methods and deep neural networks have both been tremendously successful paradigms in machine learning. In model-based methods, problem domain knowledge can be built into the constraints of the model, typically at the expense of difficulties during inference. In contrast, deterministic deep neural networks are constructed in such a way that inference is straightforward, but their architectures are rather generic and it can be unclear how to incorporate problem domain knowledge. This work aims to obtain some of the advantages of both approaches. To do so, we start with a model-based approach and unfold the iterations of its inference method to form a layer-wise structure. This results in novel neural-network-like architectures that incorporate our model-based constraints, but can be trained discriminatively to perform fast and accurate inference. This framework allows us to view conventional sigmoid networks as a special case of unfolding Markov random field inference, and leads to other interesting generalizations. We show how it can be applied to other models, such as non-negative matrix factorization, to obtain a new kind of non-negative deep neural network that can be trained using a multiplicative back propagation-style update algorithm. In speech enhancement experiments we show that our approach is competitive with conventional neural networks, while using fewer parameters.
-
- Date: Thursday, October 23, 2014
Location: Mitsubishi Electric Research Laboratories (MERL)
MERL Contact: Jonathan Le Roux
Research Area: Speech & Audio
Brief - SANE 2014, a one-day event gathering researchers and students in speech and audio from the Northeast of the American continent, will be held on Thursday October 23, 2014 at MIT, in Cambridge, MA. It is a follow-up to SANE 2012, held at Mitsubishi Electric Research Labs (MERL), and SANE 2013, held at Columbia University, which each gathered around 70 researchers and students. SANE 2014 will feature invited talks by leading researchers from the Northeast as well as Europe: Najim Dehak (MIT), Hakan Erdogan (MERL/Sabanci University), Gael Richard (Telecom ParisTech), George Saon (IBM Research), Andrew Senior (Google Research), Stavros Tsakalidis (BBN - Raytheon), and David Wingate (Lyric). It will also feature a lively poster session during lunch time, open to both students and researchers. SANE 2014 is organized by Jonathan Le Roux (MERL), Jim Glass (MIT), and John R. Hershey (MERL).
-
- Date: June 6, 2014
Where: Optical Fiber Communication Conference and Exposition (OFC)
MERL Contact: Toshiaki Koike-Akino
Research Areas: Communications, Signal Processing
Brief - Toshiaki Koike-Akino has accepted the invitation to give a talk on coded modulation formats with optimized constellations in Optical Fiber Communication Conference and Exposition (OFC 2015).
-
- Date & Time: Friday, October 18, 2013; 12:00 PM
Speaker: Dr. Shreyas Sundaram, University of Waterloo Abstract 
This talk will describe a method to stabilize a plant with a network of resource-constrained wireless nodes. As opposed to traditional networked control schemes where the nodes simply route information to and from a dedicated controller, our approach treats the network itself as the controller. Specifically, we formulate a strategy where each node repeatedly updates its state to be a linear combination of the states of neighboring nodes. We show that this causes the entire network to behave as a linear dynamical system, with sparsity constraints imposed by the network topology. We provide a numerical design procedure to determine the appropriate linear combinations for each node so that the transmissions of the nodes closest to the actuators are stabilizing. We also make connections to decentralized control theory and the concept of fixed modes to provide topological conditions under which stabilization is possible. We show that this "Wireless Control Network" requires low computational and communication overhead, simplifies transmission scheduling, and enables compositional design. We also consider the issue of security in this control scheme. Using structured system theory, we show that a certain number of malicious or misbehaving nodes can be detected and identified provided that the connectivity of the network is sufficiently high.
-
- Date & Time: Friday, October 4, 2013; 12:00 PM
Speaker: Dr. Goksel Dedeoglu, Texas Instruments
Research Area: Computer Vision
Abstract 
There are growing needs to accelerate computer vision algorithms on embedded processors for wide-ranging equipment including mobile phones, network cameras, robots, and automotive safety systems. In our Vision R&D group, we conduct various projects to understand how the vision requirements can be best addressed on Digital Signal Processors (DSP), where the compute bottlenecks are, and how we should evolve our hardware & software architectures to meet our customers' future needs. Towards this end, we build prototypes wherein we design and optimize embedded software for real-world application performance and robustness. In this talk, I will provide examples of vision problems that we have recently tackled.
-
- Date & Time: Friday, August 23, 2013; 12:00 PM
Speaker: Dr Cornel Sultan, Virginia Tech Abstract 
Coordinate coupling raises serious numerical, analysis, and control design problems that grow with the size of the system. On the other hand, decoupled dynamic equations facilitate all of the above processes since each equation can be treated independently. Unfortunately, due to the inherent heterogeneity typical of most practical, complex systems, these are not naturally decoupled so developing accurate enough decoupled approximations is of interest.
In this talk the issue of building such accurate decoupled approximations is addressed by leveraging concepts from robust control theory. Specifically, system gains (e.g. energy gain, peak to peak gain) are used to characterize the approximation error. Then some system parameters are selected to minimize this approximation error. The advantage of using system gains is that the decoupling approximation is guaranteed to be accurate over an entire class of signals (e.g. finite energy/finite peak signals). These ideas are illustrated on linearized models of tensegrity structures which are designed to yield accurate decoupled models with respect to all signals of finite energy and finite peak. Further analysis corrects several misconceptions regarding decoupling, system properties, and control design.
-
- Date & Time: Tuesday, July 23, 2013; 12:00 PM
Speaker: Dr. Sandipan Mishra, Renssealer Polytechnic Institute
MERL Host: Stefano Di Cairano Abstract 
This talk will present the breadth of research activities in the Intelligent Systems, Automation & Control Laboratory at Rensselaer Polytechnic Institute, ranging from building systems control to additive manufacturing and adaptive optics. In particular, we will focus on the modeling and control design paradigms for intelligent building systems and smart LED lighting systems. Since building systems have substantial variability of occupancy, usage, ambient environment, and physical properties over time, strategies for "model-free" control algorithms for building temperature control will be illustrated. The seminar will also discuss the state-of-the-art in feedback control of lighting systems and demonstrate the efficacy of distributed control and consensus type algorithms for these large-scale lighting systems. Finally, some interesting examples of bio-inspired estimation from blurry images for adaptive optics will be presented.
-
- Date & Time: Tuesday, July 16, 2013; 12:00 PM
Speaker: Dr. Michael Tiller, Xogeny Abstract 
Model-based System Engineering has been recognized, for some time, as a way for companies to improve their product development processes. However, change takes time in engineering and we still have only scratched the surface of what is possible. New ideas and technologies are constantly emerging that can improve a model-based approach. In this talk, I will discuss some of my past experiences with model-based system engineering in the automotive industry. I'll also discuss the shifts I see from numerical approaches to more symbolic approaches and how this manifests itself in a shift from imperative representations of engineering models to more declarative ones. I'll cover some of the interesting challenges I've seen trying to model automotive systems and how I think those challenges can be overcome moving forward. Finally, I'll talk about some of the exciting possibilities I see on the horizon for modeling.
-
- Date & Time: Wednesday, June 26, 2013; 12:00 PM
Speaker: Gabriel Rodrigues de Campos, Chalmers University Abstract 
In this talk, we consider a scenario where several vehicles have to coordinate among them in order to cross a traffic intersection. Thus, the control problem relies on the optimization of global cost function while guaranteeing collision avoidance and the satisfaction of local constraints. We propose a decentralized solution, where vehicles sequentially solve local optimization problems allowing them to cross, in a safe way, the intersection. Such approach pays a special attention to how quantify the degrees of freedom that each vehicle disposes to avoid a potential collision and lead to an adequate formalism in which collision avoidance is enforced through local state constraints at given time instants. Finally, simulations results on the efficiency, performance and optimality of the proposed approach are presented at the end of the talk.
-
- Date & Time: Thursday, May 30, 2013; 12:30 PM - 2:30 PM
Location: Vancouver, Canada
MERL Contacts: Anthony Vetro; Petros T. Boufounos; Jonathan Le Roux
Research Area: Speech & Audio
Brief - MERL is a sponsor for the first ICASSP Student Career Luncheon that will take place at ICASSP 2013. MERL members will take part in the event to introduce MERL and talk with students interested in positions or internships.
-
- Date & Time: Thursday, May 23, 2013; 12:00 PM
Speaker: Prof. Raquel Urtasun, TTI-Chicago
Research Area: Computer Vision
Abstract 
The development of autonomous systems that can effectively assist people with everyday tasks is one of the grand challenges in modern computer science. Notable examples are personal robotics for the elderly and people with disabilities, as well as autonomous driving systems which can help decrease fatalities caused by traffic accidents. To achieve full autonomy, multiple perception tasks must be solved: Autonomous systems should sense the environment, recognize the 3D world and interact with it. While most approaches have tackled individual perceptual components in isolation, I believe that the next generation of perceptual systems should reason jointly about multiple tasks.
In this talk I'll argue that there are four key aspects towards developing such holistic models: (i) learning, (ii) inference (iii) representation, and (iv) data. I'll describe efficient Markov random field learning and inference algorithms that exploit both the structure of the problem as well as parallel computation to achieve computational and memory efficiency. I'll demonstrate the effectiveness of our models on a wide variety of examples, and show representations and inference strategies that allow us to achieve state-of-the-art performance and result in several orders of magnitude speed-ups in a variety of challenging tasks, including 3D reconstruction, 3D layout parsing, object detection, semantic segmentation and free text exploitation for holistic visual recognition.
-
- Date & Time: Wednesday, May 8, 2013; 12:00 PM
Speaker: Vikrant Aute, University of Maryland
MERL Host: Christopher R. Laughman
Research Area: Data Analytics
Abstract 
Heat exchangers are a key component in any air-conditioning, heat pumping and refrigeration system. These heat exchangers (aka evaporators, condensers, indoor units, outdoor units) not only contribute significantly to the total cost of the system but also contain the most refrigerant charge. There is a continued interest in improving the designs of heat exchangers and making them more compact while reducing the cost. Compact heat exchangers help improve system performance, reduce power consumption and lower the first costs. Due to the lower internal volume, they hold lower refrigerant charge which in turn results in lower environmental impact.
In the simulation based design and optimization of compact heat exchangers, there are two main challenges. The first challenge arises from the use of computationally expensive analysis tools such as Computational Fluid Dynamics (CFD). The second challenge is the effect of scales. The use of CFD tools can make the optimization infeasible due to computing and engineering resource limitations. Furthermore, during CFD analysis, certain simplifications are made to the computational domain such as simulating a small periodic segment of a given heat transfer surface. In this talk, three technologies are introduced that assist in addressing these issues. These technologies are (1) Approximation Assisted Optimization, (2) Parallel Parameterized CFD, and (3) Multi-scale modeling of heat exchangers. These technologies together help reduce the computational effort by more than 90% and engineering time by more than 50%. Two real world applications focusing on air-to-refrigerant and liquid-to-refrigerant heat exchangers will be discussed, that demonstrate the application of these technologies.
-
- Date & Time: Thursday, March 21, 2013; 12:00 PM
Speaker: Prof. Antonio Ortega, University of Southern California
MERL Host: Anthony Vetro Abstract 
Graphs have long been used in a wide variety of problems, such analysis of social networks, machine learning, network protocol optimization, decoding of LDPCs or image processing. Techniques based on spectral graph theory provide a "frequency" interpretation of graph data and have proven to be quite popular in multiple applications.
In the last few years, a growing amount of work has started extending and complementing spectral graph techniques, leading to the emergence of "Graph Signal Processing" as a broad research field. A common characteristic of this recent work is that it considers the data attached to the vertices as a "graph-signal" and seeks to create new techniques (filtering, sampling, interpolation), similar to those commonly used in conventional signal processing (for audio, images or video), so that they can be applied to these graph signals.
In this talk, we first introduce some of the basic tools needed in developing new graph signal processing operations. We then introduce our design of wavelet filterbanks of graphs, which for the first time provides a multi-resolution, critically-sampled, frequency- and graph-localized transforms for graph signals. We conclude by providing several examples of how these new transforms and tools can be applied to existing problems. Time permitting, we will discuss applications to image processing, depth video compression, recommendation system design and network optimization.
-
- Date & Time: Friday, March 8, 2013; 12:00 PM
Speaker: Prof. Hiroshi Mamitsuka, Kyoto University Abstract 
Semi-structured data, particularly graphs, are now abundant in molecular biology. Typical examples are protein-protein interactions, gene regulatory networks, metabolic pathways, etc. To understand cellular mechanisms from this type of data, I've been working on semi-structured data, covering a wide variety of general topics in machine learning or data mining, such as link prediction, graph clustering, frequent subgraph mining, and label propagation over graphs and so on. In this talk I will focus on label propagation, in which nodes are partially labeled and the objective is to predict unknown labels using labels and links. I'll present two approaches under two different inputs in sequence: 1) only single graph and 2) multiple graphs sharing a common node set.
1) Existing methods extract features, considering either of graph smoothness or discrimination. The proposed method extracts features, considering the both two aspects, as spectral transforms. The obtained features or eigenvectors can be used to generate kernels, leading to multiple kernel learning to solve the label propagation problem efficiently.
2) Existing methods estimate weights over given graphs, like selecting the most reliable graph. This framework is however unable to consider densely connected subgraphs, which we call locally informative graphs (LIGs). The proposed method first runs spectral graph partitioning over each graph to capture LIGs in eigenvectors and then an existing method of label propagation for multiple graphs is run over the entire eigenvectors.
I will show empirical advantages of the two proposed methods by using both synthetic and real, biological networks.
-
- Date & Time: Monday, January 28, 2013; 11:00 AM
Speaker: Prof. Jen-Tzung Chien, National Chiao Tung University, Taiwan
Research Area: Speech & Audio
Abstract 
Bayesian learning provides attractive tools to model, analyze, search, recognize and understand real-world data. In this talk, I will introduce a new Bayesian group sparse learning and its application on speech recognition and signal separation. First of all, I present the group sparse hidden Markov models (GS-HMMs) where a sequence of acoustic features is driven by Markov chain and each feature vector is represented by two groups of basis vectors. The features across states and within states are represented accordingly. The sparse prior is imposed by introducing the Laplacian scale mixture (LSM) distribution. The robustness of speech recognition is illustrated. On the other hand, the LSM distribution is also incorporated into Bayesian group sparse learning based on the nonnegative matrix factorization (NMF). This approach is developed to estimate the reconstructed rhythmic and harmonic music signals from single-channel source signal. The Monte Carlo procedure is presented to infer two groups of parameters. The future work of Bayesian learning shall be discussed.
-
- Date & Time: Tuesday, December 18, 2012; 12:00 PM
Speaker: Prof. Martin Guay, Queen's University Abstract - In this presentation, an adaptive estimation technique for the estimation of time-varying parameters for a class of continuous-time nonlinear system is proposed. In the first part of the talk, we present an application of the estimation routine for the estimation of unknown heat loads and heat sinks in building systems. The technique proposed is a set-based adaptive estimation that can be used to estimate the time-varying parameters along with an uncertainty set. The proposed method is such that the uncertainty set update is guaranteed to contain the true value of the parameters. Unlike existing techniques that rely on the use of polynomial approximations of the time-varying behaviour of the parameters, the proposed technique does not require a functional representation of the time-varying behaviour of the parameter estimates.
In the second part of the talk, we consider the application of the estimation technique for the solution of a class of real-time optimization problems. It is assumed that the equations describing the dynamics of the nonlinear system and the cost function to be minimized are unknown and that the objective function is measured. The main contribution is to formulate the extremum-seeking problem as a time-varying estimation problem. The proposed approach is shown to avoid the need for averaging results which minimizes the impact of the choice of dither signal on the performance of the extremum seeking control system.
-
- Date & Time: Tuesday, December 11, 2012; 12:00 PM
Speaker: Takahiro Oku, NHK Science & Technology Research Laboratories
Research Area: Speech & Audio
Abstract - In this talk, I will present human-friendly broadcasting research conducted in NHK and research on speech recognition for real-time closed-captioning. The goal of human-friendly broadcasting research is to make broadcasting more accessible and enjoyable for everyone, including children, elderly, and physically challenged persons. The automatic speech recognition technology that NHK has developed makes it possible to create captions for the hearing impaired in real-time automatically. For sports programs such as professional sumo wrestling, a closed-captioning system has already been implemented in which captions are created by using speech recognition on a captioning re-speaker. In 2011, NHK General Television started broadcasting of closed captions for the information program "Morning Market". After the introduction of the implemented closed-captioning system, I will talk about our recent improvement obtained by an adaptation method that creates a more effective acoustic model using error correction results. The method reflects recognition error tendencies more effectively.
-
- Date & Time: Thursday, November 15, 2012; 12:00 PM
Speaker: Dr. Eduardo Torres-Jara, Worcester Polytechnic Institute
Research Area: Computer Vision
Abstract - This talk presents an alternative approach to robotic manipulation. In this approach, manipulation is mainly guided by tactile feedback as opposed to vision. The motivation behind this approach stems from the fact that manipulating an object necessarily implies coming into contact with it. As a result, directly sensing physical contact seems more important than vision to control the interaction of the object and the robot. In this work, the traditional approach of a highly precise arm guided by a vision system is replaced by one that uses a low mechanical impedance arm with dense tactile sensing and exploration capabilities.
The robots OBRERO and GoBot have been built to implement this approach. We have developed a novel tactile sensing technology and mounted our sensors on the robots' hands. These sensors are biologically inspired and present adequate features for manipulation. The success of this approach is shown by picking up objects in a poorly modeled environment. This task, simple for humans, has been a challenge for robots. The robot can deal with new, unmodeled objects. Specifically, OBRERO can gently contact, explore, lift, and place an object in a different location. It can also detect basic slippage and external forces acting on an object while it is held. These tasks can be performed successfully with very light objects, without fixtures, and on slippery surfaces. Similarly, GoBot is capable of manipulating small objects such as the stones in the game GO. Both OBRERO and GoBot perform all of their manipulations using tactile feedback.
-