Publications

Bayesian and grAphical Models for Biomedical Imaging
M. Jorge Cardoso
Ivor J. A. Simpson
Arbel, Tal
Doina Precup
Annemie Ribbens
2013-12-31
Lecture Notes in Computer Science (publié)
doi.org
Machine Learning and Interpretation in Neuroimaging
Irina Rish
Georg Langs
Leila Wehbe
Guillermo Cecchi
Kai-min Kevin Chang
Brian G Murphy
2013-12-31
Lecture Notes in Computer Science (publié)
doi.org
Experimental Algorithms
Samuel Rosat
Issmail ElHallaoui
François Soumis
Andrea Lodi
2013-10-31
Lecture Notes in Computer Science (publié)
doi.org
Adaptive Multiset Stochastic Decoding of Non-Binary LDPC Codes
Alexandru Ciobanu
Saied Hemati
Warren J. Gross
We propose a non-binary stochastic decoding algorithm for low-density parity-check (LDPC) codes over GF(q) with degree two variable nodes, c… (voir plus)alled Adaptive Multiset Stochastic Algorithm (AMSA). The algorithm uses multisets, an extension of sets that allows multiple occurrences of an element, to represent probability mass functions that simplifies the structure of the variable nodes. The run-time complexity of one decoding cycle using AMSA is O(q) for conventional memory architectures, and O(1) if a custom memory architecture is used. Two fully-parallel AMSA decoders are implemented on FPGA for two (192,96) (2,4)-regular codes over GF(64) and GF(256), both achieving a maximum clock frequency of 108 MHz. The GF(64) decoder has a coded throughput of 65 Mb/s at Eb/N0=2.4 dB when using conventional memory, while a decoder using the custom memory version can achieve 698 Mb/s at the same Eb/N0. At a frame error rate (FER) of 2×10-6 the GF(64) version of the algorithm is only 0.04 dB away from the floating-point SPA performance, and for the GF(256) code the difference is 0.2 dB. To the best of our knowledge, this is the first fully parallel non-binary LDPC decoder over GF(256) reported in the literature.
2013-08-14
IEEE Transactions on Signal Processing (publié)
doi.org
Multiscale Gossip for Efficient Decentralized Averaging in Wireless Packet Networks
Konstantinos I. Tsianos
Michael G. Rabbat
This paper describes and analyzes a hierarchical algorithm called Multiscale Gossip for solving the distributed average consensus problem in… (voir plus) wireless sensor networks. The algorithm proceeds by recursively partitioning a given network. Initially, nodes at the finest scale gossip to compute local averages. Then, using multi-hop communication and geographic routing to communicate between nodes that are not directly connected, these local averages are progressively fused up the hierarchy until the global average is computed. We show that the proposed hierarchical scheme with k=Θ(loglogn) levels of hierarchy is competitive with state-of-the-art randomized gossip algorithms in terms of message complexity, achieving ε-accuracy with high probability after O(n loglogn log[1/(ε)] ) single-hop messages. Key to our analysis is the way in which the network is recursively partitioned. We find that the above scaling law is achieved when subnetworks at scale j contain O(n(2/3)j) nodes; then the message complexity at any individual scale is O(n log[1/ε]). Another important consequence of the hierarchical construction is that the longest distance over which messages are exchanged is O(n1/3) hops (at the highest scale), and most messages (at lower scales) travel shorter distances. In networks that use link-level acknowledgements, this results in less congestion and resource usage by reducing message retransmissions. Simulations illustrate that the proposed scheme is more efficient than state-of-the-art randomized gossip algorithms based on averaging along paths.
2013-04-30
IEEE Transactions on Signal Processing (publié)
doi.org
arxiv.org
Active learning of multiple source multiple destination topologies
Pegah Sattari
Maciej Kurant
Animashree Anandkumar
Athina Markopoulou
Michael G. Rabbat
We consider the problem of inferring the topology of an M-by-N network by sending probes between M sources and N receivers. Prior work has s… (voir plus)hown that this problem can be decomposed into two parts: first, infer smaller subnetwork components (i.e., 1-by-N's or 2-by-2's) and then merge these components to identify the M-by-N topology. In this paper, we focus on the second part. In particular, we assume that a 1by-N topology is given and that all 2-by-2 components can be queried and learned using end-to-end probes. The problem is which 2-by-2's to query and how to merge them with the 1-byN, so as to exactly identify the 2-by-N topology, and optimize a number of performance metrics including measurement traffic, time complexity, and memory usage. We provide a lower bound, ⌈N/2⌉, on the number of 2-by-2's required by any active learning algorithm and we also propose a greedy algorithm that is nearoptimal and efficient in practice. It follows a bottom-up approach: at every step, it selects two receivers, queries the corresponding 2-by-2, and merges it with the given 1-by-N. The algorithm requires exactly N - 1 steps, which is much less than all (N:2) possible 2-by-2's, and it correctly identifies the 2-by-N topology.
2013-03-19
Annual Conference on Information Sciences and Systems (publié)
doi.org
Computation, Logic, Games, and Quantum Foundations. The Many Facets of Samson Abramsky
Bob. Coecke
Luke Ong
Prakash Panangaden
Samson. Abramsky
2012-12-31
Computation, Logic, Games, and Quantum Foundations (publié)
doi.org
A Semi-Parallel Successive-Cancellation Decoder for Polar Codes
Camille Leroux
Alexandre J. Raymond
Gabi Sarkis
Warren J. Gross
Polar codes are a recently discovered family of capacity-achieving codes that are seen as a major breakthrough in coding theory. Motivated b… (voir plus)y the recent rapid progress in the theory of polar codes, we propose a semi-parallel architecture for the implementation of successive cancellation decoding. We take advantage of the recursive structure of polar codes to make efficient use of processing resources. The derived architecture has a very low processing complexity while the memory complexity remains similar to that of previous architectures. This drastic reduction in processing complexity allows very large polar code decoders to be implemented in hardware. An N=217 polar code successive cancellation decoder is implemented in an FPGA. We also report synthesis results for ASIC.
2012-12-31
IEEE Transactions on Signal Processing (publié)
doi.org
Statistical Language and Speech Processing
Yoshua Bengio
Fethi Bougares
Horia Cucu
Corneliu Burileanu
Myung-Jae Kim
Il-ho Yang
Jordan Rodu
Dean Phillips Foster
Weichen Wu
Stefan Bott
Felix Stahlberg
Luis A. Trindade
Hao Wang
2012-12-31
Lecture Notes in Computer Science (publié)
doi.org
Algorithms in Bioinformatics
P. Agarwal
Tatsuya Akutsu
Amir Amihood
Alberto Apostolico
C. Benham
Gary Gustaf Benson
Mathieu Blanchette
Nadia El-Mabrouk
Olivier Gascuel
Raffaele Giancarlo
R. Guigó
Michael Hallet
D. Huson
G. Kucherov
Michelle R. Lacey
Jens Lagergren
Giuseppe Lancia
Gad M. Landau
Thierry. Lecroq
B. Moret … (voir 21 de plus)
S. Morishita
Elchanan Mossel
Vincent Moulton
Lior S. Pachter
Knut Reinert
I. Rigoutsos
David Sankoff
Sophie Schbath
Eran Segal
Charles Semple
J. Setubal
Roded Sharan
S. Skiena
Jens Stoye
Esko Ukkonen
Lisa Allen Vawter
Alfonso Valencia
Tandy J. Warnow
Lusheng Wang
Rita Casadio
Gene Myers
2012-09-30
Lecture Notes in Computer Science (publié)
doi.org
Theano: Deep Learning on GPUs with Python
James Bergstra
Frédéric Bastien
Olivier Breuleux
Pascal Lamblin
Razvan Pascanu
Olivier Delalleau
Guillaume Desjardins
David Warde-Farley
Ian G Goodfellow
Arnaud Bergeron
Yoshua Bengio
In this paper, we present Theano 1 , a framework in the Python programming language for defining, optimizing and evaluating expressions invo… (voir plus)lving high-level operations on tensors. Theano offers most of NumPy’s functionality, but adds automatic symbolic differentiation, GPU support, and faster expression evaluation. Theano is a general mathematical tool, but it was developed with the goal of facilitating research in deep learning. The Deep Learning Tutorials 2 introduce recent advances in deep learning, and showcase how Theano
2011-12-31
(publié)
www.semanticscholar.org
Delayed Stochastic Decoding of LDPC Codes
Ali Naderi
Shie Mannor
Mohamad Sawan
Warren J. Gross
A new stochastic decoding algorithm, called Delayed Stochastic (DS) decoding, is introduced to implement low-density-parity-check (LDPC) dec… (voir plus)oders. The delayed stochastic decoding uses an alternative method to track probability values, which results in reduction of hardware complexity and memory requirement of the stochastic decoders. It is therefore suitable for fully-parallel implementation of long LDPC codes with applications in optical communications. Two decoders are implemented using the DS algorithm for medium (2048, 1723) and long (32768, 26624) LDPC codes. The decoders occupy 3.93- mm2 and 56.5- mm2 silicon area using 90-nm CMOS technology and provide maximum core throughputs of 172.4 and 477.7 Gb/s at [(Eb)/(No)]=5.5 and 4.8 dB, respectively.
2011-10-31
IEEE Transactions on Signal Processing (publié)
doi.org