IEEE

Archive for the ‘Uncategorized’ Category

Talk: Neural Network Interpretability using Full-Gradient Representation

Wednesday, January 1st, 2020
IEEE Signal Processing Society, Bangalore Chapter and Department of Computational and Data Sciences, 
Indian Institute of Science Invite you to the following talk:
 
SPEAKER   : Suraj Srinivas, PhD Scholar, Idiap Research Institute and EPFL, Switzerland
TITLE          : “Neural Network Interpretability using Full-Gradient Representation”
Venue            :  #102 CDS Seminar Hall
Date & Time :  Jan  07, 2020, 12:00 Noon

ABSTRACT:

In this talk, I will introduce a new tool for interpreting neural net responses, namely full-gradients, which decomposes the neural net response into input sensitivity and per-neuron sensitivity components. This is the first proposed representation which satisfies two key properties: completeness and weak dependence, which provably cannot be satisfied by any saliency map-based interpretability method. For convolutional nets, we also propose an approximate saliency map representation, called FullGrad, obtained by aggregating the full-gradient components. We experimentally evaluate the usefulness of FullGrad in explaining model behaviour with two quantitative tests: pixel perturbation and remove-and-retrain. Our experiments reveal that our method explains model behaviour correctly, and more comprehensively than other methods in the literature. Visual inspection also reveals that our saliency maps are sharper and more tightly confined to object regions than other methods. This talk is based on our recent NeurIPS 2019 paper titled “Full-Gradient Representation for Neural Network Visualization”.

BIOGRAPHY:
Suraj Srinivas is a 3rd year PhD research assistant at Idiap Research Institute and EPFL, Switzerland. He works with Prof. Francois Fleuret on analytically understanding deep learning architectures. Before that, he completed his M.Sc.(Engg.) at CDS, IISc, where he worked with Prof. Venkatesh Babu on neural network compression. His research interest are broadly relating to the robustness, adaptability and interpretability of deep neural networks.

Host Faculty: Prof. Venkatesh Babu

Talk on Speech Articulation Disorders

Wednesday, January 1st, 2020

IEEE Signal Processing Society, Bangalore Chapter

and
Department of Electrical Engineering
Indian Institute of Science (IISc), Bangalore
invite you to the following talk
Title: Utilizing Real-time MRI to Investigate Speech Articulation Disorders
Date and time: January 10, 2020; 11:30AM (Coffee will be served at 11:15AM)
Venue: Multimedia Classroom, Department of Electrical Engineering, IISc.
Speaker: Christina Hagedorn, PhD, SLP, CCC-SLP, City University of New York – College of Staten Island
Abstract:
Over the past two decades, real-time Magnetic Resonance Imaging (rtMRI), elaborating traditional medical MRI, has played a critical role in studying a variety of biological movement patterns. Through collaboration between engineers and speech scientists, rtMRI technology has been applied to the study of speech production. Through semi-automatic detection of air-tissue boundaries and estimation of articulatory kinematics using pixel intensity time functions, rtMRI can be used to quantitatively analyze speech production patterns in both typical and disordered populations. In this work, rtMRI is demonstrated to shed light on aspects of speech produced by individuals with tongue cancer and individuals with Apraxia of Speech that would not be possible using tools providing more limited spatiotemporal information about vocal tract shaping.
Biography of the speaker:
Christina Hagedorn is an assistant professor of Linguistics and director of the Motor Speech Laboratory at the City University of New York (CUNY) – College of Staten Island. Her research focuses primarily on disordered speech production. Her work aims to shed light on the precise nature of articulatory breakdowns in disordered speech and how this can inform theories of unimpaired speech production, as well as lead to refinement of the therapeutic techniques used to address these speech deficits.

She received her Ph.D. in Linguistics from the University of Southern California, where she was a member of the Speech Production and Articulation kNowledge (SPAN) Group, the USC Phonetics and Phonology Group, and was a Hearing and Communication Neuroscience pre-doctoral fellow. She received her clinical training in Communicative Sciences and Disorders at New York University, and holds a certificate of clinical competency in Speech and Language Pathology (CCC-SLP).

Talk: New Twists for New Tricks

Wednesday, January 1st, 2020

The IEEE Signal Processing Society, Bangalore Chapter and

Indian Institute of Science

Cordially invite you to the following talk on

New Twists for New Tricks, Making Audio Deep Learning Practical

Speaker: Prof. Paris Smaragdis, University of Illinois at Urbana-Champaign.

Date and Time: 6th Jan, 2020, 4pm, Refreshments: 3:45pm

Venue: ECE Golden Jubilee Seminar Hall.

Talk flyer

Seminar: A fine-grained perspective onto object interactions

Tuesday, December 17th, 2019

IEEE Signal Processing Society, Bangalore Chapter and Department of Computational and Data Sciences, 

Indian Institute of Science Invite you to the following talk:

SPEAKER   :  Prof. Dima Damen, Associate Professor (Reader), University of Bristol, UK 

TITLE          : A fine-grained perspective onto object interactions 

Venue            :  #102, CDS Seminar Hall

Date & Time :  Dec 26, 2019, 04:00 PM

ABSTRACT:

This talk aims to argue for a fine-grained perspective onto human-object interactions, from video sequences. The talk will present approaches for determining skill or expertise from video sequences [CVPR 2019], assessing action ‘completion’ – i.e. when an interaction is attempted but not completed [BMVC 2018], dual-domain and dual-time learning [CVPR 2019, ICCVW 2019] as well as multi-modal approaches using vision, audio and language [ICCV 2019, BMVC 2019].

This talk will also introduce EPIC-KITCHENS [ECCV 2018], the recently released largest dataset of object interactions in people’s homes, recorded using wearable cameras. The dataset includes 11.5M frames fully annotated with objects and actions, based on unique annotations from the participants narrating their own videos, thus reflecting true intention. Three open challenges are now available on object detection, action recognition and action anticipation [http://epic-kitchens.github.io

BIOGRAPHY:

Dima Damen is a Reader (Associate Professor) in Computer Vision at the University of Bristol, United Kingdom. Received her PhD from the University of Leeds, UK (2009). Dima’s research interests are in the automatic understanding of object interactions, actions and activities using static and wearable visual (and depth) sensors. Dima co-chaired BMVC 2013, is area chair for BMVC (2014-2018), associate editor of IEEE TPAMI (2019-) and associate editor of Pattern Recognition (2017-). She was selected as a Nokia Research collaborator in 2016, and as an Outstanding Reviewer in ICCV17, CVPR13 and CVPR12. She currently supervises 6 PhD students, and 4 postdoctoral researchers. More details at: [http://dimadamen.github.io]

Host Faculty: Prof. Venkatesh Babu

__________________________________________________________________________________________________________________

                        ALL ARE WELCOME

Talk: From compressed sensing to DL: tasks, structures, and models

Monday, December 16th, 2019

IEEE Signal Processing Society, Bangalore Chapter

and

Department of Electrical Engineering

Indian Institute of Science (IISc), Bangalore

invite you to the following talk

Title: From compressed sensing to deep learning: tasks, structures, and models.

Date and time: December 18, 2019; 11.30 AM.

Coffee will be served during the talk.

Venue: Multimedia Classroom, Department of Electrical Engineering, IISc.

Speaker: Prof. Yonina Eldar, Weizmann Institute of Science, Israel.

Host faculty: Dr. Chandra Sekhar Seelamantula, EE, IISc.

Abstract: 

The famous Shannon-Nyquist theorem has become a landmark in the development of digital signal and image processing. However, in many modern applications, the signal bandwidths have increased tremendously, while the acquisition capabilities have not scaled sufficiently fast. Consequently, conversion to digital has become a serious bottleneck.  Furthermore, the resulting digital data requires storage, communication and processing at very high rates which is computationally expensive and requires large amounts of power.  In the context of medical imaging sampling at high rates often translates to high radiation dosages, increased scanning times, bulky medical devices, and limited resolution.

In this talk, we present a framework for sampling and processing a large class of wideband analog signals at rates far below Nyquist in space, time and frequency, which allows to dramatically reduce the number of antennas, sampling rates and band occupancy.

 

Our framework relies on exploiting signal structure and the processing task.  We consider applications of these concepts to a variety of problems in communications, radar and ultrasound imaging and show several demos of real-time sub-Nyquist prototypes including a wireless ultrasound probe, sub-Nyquist MIMO radar, super-resolution in microscopy and ultrasound, cognitive radio, and joint radar and communication systems. We then discuss how the ideas of exploiting the task, structure and model can be used to develop interpretable model-based deep learning methods that can adapt to existing structure and are trained from small amounts of data. These networks achieve a more favorable trade-off between increase in parameters and data and improvement in performance, while remaining interpretable.

Biography of the speaker:

Yonina C. Eldar received the B.Sc. degree in Physics in 1995 and the B.Sc. degree in Electrical Engineering in 1996 both from Tel-Aviv University (TAU), Tel-Aviv, Israel, and the Ph.D. degree in Electrical Engineering and Computer Science in 2002 from the Massachusetts Institute of Technology (MIT), Cambridge. From January 2002 to July 2002 she was a Postdoctoral Fellow at the Digital Signal Processing Group at MIT.

She is currently a Professor in the Department of Mathematics and Computer Science, Weizmann Institute of Science, Rehovot, Israel. She was previously a Professor in the Department of Electrical Engineering at the Technion, where she held the Edwards Chair in Engineering. She is also a Visiting Professor at MIT, a Visiting Scientist at the Broad Institute, and an Adjunct Professor at Duke University and was a Visiting Professor at Stanford. She is a member of the Israel Academy of Sciences and Humanities (elected 2017), an IEEE Fellow and a EURASIP Fellow.

Dr. Eldar has received numerous awards for excellence in research and teaching, including the IEEE Signal Processing Society Technical Achievement Award (2013), the IEEE/AESS Fred Nathanson Memorial Radar Award (2014), and the IEEE Kiyo Tomiyasu Award (2016). She was a Horev Fellow of the Leaders in Science and Technology program at the Technion and an Alon Fellow. She received the Michael Bruno Memorial Award from the Rothschild Foundation, the Weizmann Prize for Exact Sciences, the Wolf Foundation Krill Prize for Excellence in Scientific Research, the Henry Taub Prize for Excellence in Research (twice), the Hershel Rich Innovation Award (three times), the Award for Women with Distinguished Contributions, the Andre and Bella Meyer Lectureship, the Career Development Chair at the Technion, the Muriel & David Jacknow Award for Excellence in Teaching, and the Technion’s Award for Excellence in Teaching (twice). She received several best paper awards and best demo awards together with her research students and colleagues including the SIAM outstanding Paper Prize and the IET Circuits, Devices and Systems Premium Award, and was selected as one of the 50 most influential women in Israel.

She was a member of the Young Israel Academy of Science and Humanities and the Israel Committee for Higher Education. She is the Editor in Chief of Foundations and Trends in Signal Processing, a member of the IEEE Sensor Array and Multichannel Technical Committee and serves on several other IEEE committees. In the past, she was a Signal Processing Society Distinguished Lecturer, member of the IEEE Signal Processing Theory and Methods and Bio Imaging Signal Processing technical committees, and served as an associate editor for the IEEE Transactions On Signal Processing, the EURASIP Journal of Signal Processing, the SIAM Journal on Matrix Analysis and Applications, and the SIAM Journal on Imaging Sciences. She was Co-Chair and Technical Co-Chair of several international conferences and workshops.

She is author of the book “Sampling Theory: Beyond Bandlimited Systems” and co-author of the books “Compressed Sensing” and “Convex Optimization Methods in Signal Processing and Communications,” all published by Cambridge University Press.

Formation of Ramaiah Institute of Tech. SPS Student Branch Chapter

Wednesday, October 9th, 2019

We are happy to announce the formation of the Ramaiah Institute of Technology Signal Processing Society Student Branch Chapter from October 2, 2019. 

IEEE SP Chapter talk: Coherence Diversity in Multi-User Networks

Friday, March 8th, 2019

Department of Electrical Communication Engineering (ECE), IISc

and

IEEE SPS Bangalore Chapter

invite you to the following seminar:

 

Title: Coherence Diversity in Multi-User Networks

Speaker:  Prof. Aria Nosratinia
Electrical Engineering Department
University of Texas at Dallas

Date/Time: 18 March 2019, 4 PM

Venue: Golden Jubilee Seminar Hall, Dept. of ECE

Abstract:
Although links in a wireless network may easily experience different
coherence conditions, the literature in communication and information
theory has mostly concentrated on coherence intervals of equal length
throughout the network. This talk explores new and exciting developments
in the field of non-uniform fading dynamics, where the disparity of
fading intervals can lead to new gains in multi-user networks that are
distinct from previously known phenomena. Product superposition, a new
tool developed to address non-uniform dynamics, will be introduced.
We begin by studying the application of this tool in the 2-user
broadcast channel. The results will be extended to the multi-user
broadcast channel. Disparity in either coherence bandwidth, or both
coherence time & bandwidth, will be discussed. Time permitting, the
interplay with non-uniform or stale CSI, and the interactions of
product superposition with retrospective interference alignment will
be discussed.

Speaker’s Bio:
Aria Nosratinia is Erik Jonsson Distinguished Professor and
associate head of the Electrical Engineering Department at the
University of Texas at Dallas. He received his Ph.D. in Electrical
and Computer Engineering from the University of Illinois at
Urbana-Champaign in 1996. He has held visiting appointments at
Princeton University, Rice University, and UCLA.  His interests
lie in the broad area of information theory and signal processing,
with applications in wireless communication. Dr. Nosratinia is a
fellow of IEEE for contributions to multimedia and wireless
communications. He has served as editor and area editor for the
IEEE Transactions on Wireless Communications, and editor for the
IEEE Transactions on Information Theory, IEEE Transactions on
Image Processing, IEEE Signal Processing Letters, IEEE Wireless
Communications, and Journal of Circuits, Systems, and Computers.
He has received the National Science Foundation career award, and
the outstanding service award from the IEEE Signal Processing
Society, Dallas Chapter. He has served on the organizing committees
and technical program committees for a number of conferences, most
recently as the general co-chair of ITW 2018. He was named a highly
cited researcher by Clarivate Analytics (formerly Thomson Reuters).

____________
ALL ARE WELCOME

Seminar: Role and Strengths of Adversarial Perturbations in DL

Wednesday, February 20th, 2019

 

Department of Computational and Data Sciences and IEEE SP Bangalore Chapter invite you for the following seminar

SPEAKER  : Dr. Mayank Vatsa and Dr. Richa Singh
TITLE         : Role and Strengths of Adversarial Perturbations in Deep Learning
Date/Time   : February 21, 2019 (Thursday) 11:00 AM
Venue          : 102 CDS Seminar Hall.


ABSTRACT

Deep neural network architecture based models have high expressive power and learning ca-pacity. Due to several advancements, deep learning based models have shown very high accuracies on challenging databases including face databases. However, they are essentially a black box method since it is not easy to mathematically formulate the functions that are learned within its many layers of repre-sentation. Realizing this, many researchers have started to design methods to exploit the drawbacks of deep learning based algorithms questioning their robustness and exposing their singularities.

Adversarial attacks on automated classification systems has been an area of interest for a long time. In 2002, Ratha et al. proposed eleven points of attacks on a biometric/face recognition system. For in-stance, an adversary can operate at the input/image level or the decision level, and lead to incorrect face recognition results. The research on adversarial learning for attacking face recognition systems has three key components: (i) creating adversarial images, (ii) detecting whether an image is adversely altered or not, and (iii) mitigating the effect of the adversarial perturbation process. These adversaries create dif-ferent kinds of effect on the input and detecting them requires the application of a combination of hand-crafted as well as learnt features; for instance, some of the existing attacks can be detected using prin-cipal components while some hand-crafted attacks can be detected using well defined image processing operations. Therefore, it is important to detect the adversarial perturbations and mitigate the effect caused due to such adversaries using ensemble of defense algorithms. While majority of the research in adversarial perturbations focus on attacking deep learning models, in this talk, we will also connect how adversarial perturbations can be used for building Trusted-AI systems. With two threads on this direc-tion, we will discuss privacy preserving applications in faces as well as a novel concept of Data Fine-tuning.

BIOGRAPHY

Mayank Vatsa received the M.S. and Ph.D. degrees in computer science from West Virginia University, USA, in 2005 and 2008, respectively. He is currently the Head of the Infosys Center for Artificial Intelli-gence, an Associate Professor with the IIIT-Delhi, India, and an Adjunct Associate Professor with West Virginia University, USA. He has co-edited a book Deep learning in Biometrics and co-authored over 250 research papers. His areas of interest are biometrics, image processing, machine learning, computer vi-sion, and information fusion. He is a Senior Member of IEEE and ACM. He was a recipient of A. R. Krish-naswamy Faculty Research Fellowship at the IIIT-Delhi, the FAST Award Project by DST, India, and several Best Paper and Best Poster Awards at international conferences. He is also the recipient of the prestigious Swarnajayanti fellowship award from Government of India. He is an Area Chair of the Information Fusion (Elsevier), General Co-Chair of IJCB 2020, and the PC Co-Chair of the ICB 2013 and IJCB 2014. He has served as the Vice President (Publications) of the IEEE Biometrics Council where he started the IEEE Transactions on Biometrics, Behavior, And Identity Science.

 

Richa Singh received the Ph.D. degree in computer science from West Virginia University, Morgantown, USA, in 2008. She  is  currently an  Associate Dean of  Alumni and  Communications,  an Associate Professor with the IIIT-Delhi, India, and an Adjunct Associate Professor with West Virginia University. She has co-edited book Deep Learning in Biometrics and has delivered tutorials on deep learning and domain adap-tation in ICCV 2017, AFGR 2017, and IJCNN 2017. Her areas of interest are pattern recognition, machine learning, and biometrics. She is a fellow of IAPR and a Senior Member of IEEE and ACM. She was a recipient of the Kusum and Mohandas Pai Faculty Research Fellowship at the IIIT-Delhi, the FAST Award by the Department of Science and Technology, India, and several best paper and best poster awards in interna-tional conferences. She has also served as the Program Co-Chair of BTAS 2016 and IWBF 2018, and a General Co-Chair of ISBA 2017. She is currently serving as a Program Co-Chair of AFGR 2019 and IJCB 2020. She is serving as the Vice President (Publications) of the IEEE Biometrics Council. She is an Editorial Board Member of Information Fusion (Elsevier), an Associate Editor of Pattern Recognition, Computer Vision and Image Understanding, and the EURASIP Journal on Image and Video Processing (Springer).

____________
ALL ARE WELCOME

Seminar: Multisensory Integration in the Brain

Wednesday, February 13th, 2019

 

Department of Computational and Data Sciences and IEEE SP Bangalore Chapter invite you for the following seminar

SPEAKER  : Dr. Shirin Dora, Post Doc

TITLE         : Multisensory Integration in the Brain

Date/Time   : February 14, 2019 (Thursday) 04:00 PM

Venue          : 102 CDS Seminar Hall.

 ABSTRACT

Multisensory integration is a phenomenon by which the brain infers coherent and robust representations using incoming sensory information in different modalities. It plays a significant role in perception as well as all cognitive functions from memory to decision-making. Because of its inherent multimodal nature, it is harder to study in experiments and many open questions exist regarding its underlying neural mechanisms. In my research, I approach this problem from two different perspectives using computational models in conjunction with experimental data. In the first method, I focus on understanding the neurobiological mechanisms that might support multisensory integration. I will show that deep neural networks trained using predictive coding can account for neuronal properties like selectivity and sparsity along the visual cortical hierarchy. In the second method focus shifts to identifying the underlying structures necessary for multisensory integration rather than the intermediate mechanisms that yield these structures

 BIOGRAPHY

Shirin Dora completed his PhD in machine learning from Nanyang Technological University in Singapore. His research focused on developing biologically plausible learning approaches for spiking neural networks. During his PhD, he developed a keen interest in the mechanisms of perception and cognition in the brain. This led him to pursue a post-doctoral research in computational neuroscience in the cognitive and systems neuroscience group at the University of Amsterdam. In his postdoctoral research, he collaborates with experimentalists in building models of perception and multisensory integration in the brain.

 

__________________________________________________________________________________________________

                                                               ALL ARE WELCOME

Seminar: Weakly-supervised and incremental learning

Saturday, December 22nd, 2018