total 99took 0.19s

CacheShield: Protecting Legacy Processes Against Cache AttacksSep 06 2017Cache attacks pose a threat to any code whose execution flow or memory accesses depend on sensitive information. Especially in public clouds, where caches are shared across several tenants, cache attacks remain an unsolved problem. Cache attacks rely ... More

RELOAD+REFRESH: Abusing Cache Replacement Policies to Perform Stealthy Cache AttacksApr 12 2019Caches have become the prime method for unintended information extraction across logical isolation boundaries. Even Spectre and Meltdown rely on the cache side channel, as it provides great resolution and is widely available on all major CPU platforms. ... More

Submodular Welfare MaximizationNov 21 2013An overview of different variants of the submodular welfare maximization problem in combinatorial auctions. In particular, I studied the existing algorithmic and game theoretic results for submodular welfare maximization problem and its applications in ... More

On the Global Existence for the Axisymmetric Euler-Boussinesq System in Critical Besov SpacesMar 16 2012This paper is devoted to the global existence and uniqueness results for the three-dimensional Boussinesq system with axisymmetric initial data $v^{0}{\in}B_{2,1}^{5/2}(\RR^3)$ and$ ${\rho}^{0}{\in}B_{2,1}^{1/2}(\RR^3)\cap L^{p}(\RR^3)$ with $p>6.$ This ... More

Inviscid limit for axisymmetric stratified Navier-Stokes systemJun 05 2012This paper is devoted to the study of the Cauchy problem for the stratified Navier-Stokes system in space dimension three. In the first part of the paper, we prove the existence of a unique global solution $(v_\nu,\rho_\nu)$ for this system with axisymmetric ... More

Global existence and uniqueness for a non linear Boussinesq system in dimension twoMar 22 2012We study the global well-posedness of a two-dimensional Boussinesq system which couples the incompressible Euler equation for the velocity and a transport equation with fractional diffusion of type $|\DD|^{\alpha}$ for the temperature. We prove that for ... More

Symmetry Transformation in Extended Phase Space: the Harmonic Oscillator in the Husimi RepresentationFeb 04 2008In a previous work the concept of quantum potential is generalized into extended phase space (EPS) for a particle in linear and harmonic potentials. It was shown there that in contrast to the Schr\"odinger quantum mechanics by an appropriate extended ... More

Likelihood Analysis of CMB Temperature and Polarization Power SpectraJan 03 2008Apr 24 2012Microwave background temperature and polarization observations are a powerful way to constrain cosmological parameters if the likelihood function can be calculated accurately. The temperature and polarization fields are correlated, partial sky coverage ... More

A Survey of Natural Language Generation Techniques with a Focus on Dialogue Systems - Past, Present and Future DirectionsJun 02 2019One of the hardest problems in the area of Natural Language Processing and Artificial Intelligence is automatically generating language that is coherent and understandable to humans. Teaching machines how to converse as humans do falls under the broad ... More

Electronic Structure Properties of UO2 as a Mott InsulatorJul 06 2019In this work using the density functional theory (DFT), we have studied the structural, electronic and magnetic properties of uranium dioxide with antiferromagnetic 1k-, 2k-, and 3k-order structures. Ordinary approximations in DFT, such as the local density ... More

Clustering and Labelling Auction Fraud DataAug 22 2018Although shill bidding is a common auction fraud, it is however very tough to detect. Due to the unavailability and lack of training data, in this study, we build a high-quality labeled shill bidding dataset based on recently collected auctions from eBay. ... More

Incompressible limit for the 2D isentropic Euler system with critical initial dataMar 17 2012We study in this paper the low Mach number limit for the 2d isentropic Euler system with ill-prepared initial data belonging to the critical Besov space $B_{2,1}^2$. By combining Strichartz estimates with the special structure of the vorticity we prove ... More

First-principles study of UO$_2$ lattice thermal-conductivity: A simple descriptionJul 09 2019Modeling the high-T paramagnetic state of bulk UO$_2$ by a non-spin-polarized calculation and neglecting the Hubbard-U correction for the f electrons in U atoms, the lattice thermal conductivity of bulk UO$_2$ is investigated by the exact solution of ... More

Prior Independent Equilibria and Linear Multi-dimensional Bayesian GamesApr 09 2018We show that a Bayesian strategy map profile is a Bayesian Nash Equilibrium independent of any prior if and only if the Bayesian strategy map profile, evaluated at any type profile, is the Nash equilibrium of the so-called local deterministic game corresponding ... More

Marcinkiewicz Law of Large Numbers for Outer-products of Heavy-tailed, Long-range Dependent DataJan 11 2015The Marcinkiewicz Strong Law, $\displaystyle\lim_{n\to\infty}\frac{1}{n^{\frac1p}}\sum_{k=1}^n (D_{k}- D)=0$ a.s. with $p\in(1,2)$, is studied for outer products $D_k=X_k\overline{X}_k^T$, where $\{X_k\},\{\overline{X}_k\}$ are both two-sided (multivariate) ... More

Properties and use of CMB power spectrum likelihoodsFeb 04 2009Apr 08 2009Fast robust methods for calculating likelihoods from CMB observations on small scales generally rely on approximations based on a set of power spectrum estimators and their covariances. We investigate the optimality of these approximation, how accurate ... More

Scraping and Preprocessing Commercial Auction Data for Fraud ClassificationJun 02 2018Jun 17 2018In the last three decades, we have seen a significant increase in trading goods and services through online auctions. However, this business created an attractive environment for malicious moneymakers who can commit different types of fraud activities, ... More

Nontrivial solutions of systems of nonlocal Caputo fractional BVPsJan 29 2016We discuss the existence, non-existence and multiplicity of nontrivial solutions for systems of Caputo fractional differential equations subject to nonlocal boundary conditions. Our methodology relies on classical fixed point index and we make use of ... More

Efficient Local Density Estimation Strategy for VANETsFeb 18 2014Local vehicle density estimation is increasingly becoming an essential factor of many vehicular ad-hoc network applications such as congestion control and traffic state estimation. This estimation is used to get an approximate number of neighbors within ... More

BSK-WBSN: Biometric Symmetric Keys to Secure Wireless Body Sensors NetworksOct 08 2011The Wireless Sensors Network (WSN) is an emergent technology resulting from progress of various fields. Many applications of networks WSN are born. One of the applications which have an operational effectiveness relates to the field of health and allows ... More

Building High-Quality Auction Fraud DatasetJun 10 2019Given the magnitude of online auction transactions, it is difficult to safeguard consumers from dishonest sellers, such as shill bidders. To date, the application of machine learning to auction fraud detection has been limited. Shill Bidding (SB) is a ... More

Building High-Quality Auction Fraud DatasetJun 10 2019Jun 28 2019Given the magnitude of online auction transactions, it is difficult to safeguard consumers from dishonest sellers, such as shill bidders. To date, the application of machine learning to auction fraud detection has been limited. Shill Bidding (SB) is a ... More

Digital Hurewicz Theorem and Digital Homology theoryFeb 06 2019In this paper, we develop homology groups for digital images based on cubical singular homology theory for topological spaces. Using this homology, we present digital Hurewicz theorem for the fundamental group of digital images. We also show that the ... More

Digital Hurewicz Theorem and Digital Homology TheoryFeb 06 2019Jun 18 2019In this paper, we develop homology groups for digital images based on cubical singular homology theory for topological spaces. Using this homology, we present digital Hurewicz theorem for the fundamental group of digital images. We also show that the ... More

Convergence Rates and Decoupling in Linear Stochastic Approximation AlgorithmsJan 11 2015Almost sure convergence rates for linear algorithms $h_{k+1} = h_k +\frac{1}{k^\chi} (b_k-A_kh_k)$ are studied, where $\chi\in(0,1)$, $\{A_{k}\}_{k=1}^\infty$ are symmetric, positive semidefinite random matrices and $\{b_{k}\}_{k=1}^\infty$ are random ... More

Digital Hurewicz Theorem and Digital Homology theoryFeb 06 2019Feb 28 2019In this paper, we develop homology groups for digital images based on cubical singular homology theory for topological spaces. Using this homology, we present digital Hurewicz theorem for the fundamental group of digital images. We also show that the ... More

Robust Evaluation of Language-Brain Encoding ExperimentsApr 04 2019Language-brain encoding experiments evaluate the ability of language models to predict brain responses elicited by language stimuli. The evaluation scenarios for this task have not yet been standardized which makes it difficult to compare and interpret ... More

Work function tuning of graphene oxide by using cesium applied to low work function tethersJun 25 2019Low Work Function Tethers (LWT) is long conductors with a segment coated with a material that has loosely-bounded electrons. Unlike a standard bare tether equipped with an active electron emitter, LWTs close the electrical circuit (cathodic contact) with ... More

Streaming Verification in Data AnalysisSep 18 2015Streaming interactive proofs (SIPs) are a framework to reason about outsourced computation, where a data owner (the verifier) outsources a computation to the cloud (the prover), but wishes to verify the correctness of the solution provided by the cloud ... More

Toward a Boundary Regional Control Problem for Boolean Cellular AutomataJun 16 2016Jun 27 2017An important question to be addressed regarding system control on a time interval $[0, T]$ is whether some particular target state in the configuration space is reachable from a given initial state. When the target of interest refers only to a portion ... More

On the Capacity Region of ALOHA Protocol for the Internet of ThingsMay 27 2016Accommodating the needs of a large number of diverse users in the Internet of Things (IoT), notably managing how the users access the common channel, has posed unique challenges to the network designers. In this paper, we study a heterogeneous IoT network ... More

The Bottom-Up Position Tree Automaton, the Father Automaton and their Compact VersionsMay 22 2018The conversion of a given regular tree expression into a tree automaton has been widely studied. However, classical interpretations are based upon a Top-Down interpretation of tree automata. In this paper, we propose new constructions based on the Gluskov's ... More

Range Counting Coresets for Uncertain DataApr 15 2013We study coresets for various types of range counting queries on uncertain data. In our model each uncertain point has a probability density describing its location, sometimes defined as k distinct locations. Our goal is to construct a subset of the uncertain ... More

Usability of Humanly Computable PasswordsDec 11 2017May 24 2018Reusing passwords across multiple websites is a common practice that compromises security. Recently, Blum and Vempala have proposed password strategies to help people calculate, in their heads, passwords for different sites without dependence on third-party ... More

On the gravitational instability in the Newtonian limit of MOGApr 13 2017We have found some analytical cosmological solutions to MOdified Gravity (MOG). These solutions describe different evolutionary epochs of an isotropic and homogeneous universe. During each epoch, the evolution of cosmological perturbation is studied in ... More

Computing all border bases for ideals of pointsJul 07 2017In this paper we consider the problem of computing all possible order ideals and also sets connected to 1, and the corresponding border bases, for the vanishing ideal of a given finite set of points. In this context two different approaches are discussed: ... More

Regional Control of Boolean Cellular AutomataJun 16 2016An interesting problem in extended physical systems is that of the regional control, i.e., how to add a suitable control at the boundary or inside a region of interest so that the state of such region is near to a desired one. Many physical problems are ... More

Control of cellular automataJun 11 2012We study the problem of master-slave synchronization and control of totalistic cellular automata (CA) by putting a fraction of sites of the slave equal to those of the master and finding the distance between both as a function of this fraction. We present ... More

Irregular Motion of a Falling Spherical Object Through Non-Newtonian FluidAug 17 2011The falling of an object through a non-Newtonian fluid is an interesting problem, depending on the details of the rheology of the fluid. In this paper we report on the settling of spherical objects through two non-Newtonian fluids: Laponite and hair Gel. ... More

Performance Analysis of Massive MIMO Multi-Way Relay Networks with Low-Resolution ADCsApr 19 2018Dec 07 2018This paper considers a multiuser multi-way relay network where users exchange their information via a relay equipped with a large-scale antenna array. We consider the practical case that the analog-to-digital converters (ADCs) equipped for the relay antenna ... More

RATM: Recurrent Attentive Tracking ModelOct 29 2015Apr 28 2016We present an attention-based modular neural framework for computer vision. The framework uses a soft attention mechanism allowing models to be trained with gradient descent. It consists of three modules: a recurrent attention module controlling where ... More

Efficient Decoding of Synchronized Colliding LoRa SignalsFeb 14 2019In LoRa (Long Range), when a collision occurs in the network, each end-device has to retransmit its colliding frame, which reduces the throughput, and increases the energy consumption of the end-devices and the delay of the frames. In this paper, we propose ... More

Streaming Verification of Graph PropertiesFeb 26 2016Oct 04 2016Streaming interactive proofs (SIPs) are a framework for outsourced computation. A computationally limited streaming client (the verifier) hands over a large data set to an untrusted server (the prover) in the cloud and the two parties run a protocol to ... More

Regional Control of Probabilistic Cellular AutomataJul 11 2018Probabilistic Cellular Automata are extended stochastic systems, widely used for modelling phenomena in many disciplines. The possibility of controlling their behaviour is therefore an important topic. We shall present here an approach to the problem ... More

An efficient cntfet-based 7-input minority gateMar 09 2013Complementary metal oxide semiconductor technology (CMOS) has been faced critical challenges in nano-scale regime. CNTFET (Carbon Nanotube Field effect transistor) technology is a promising alternative for CMOS technology. In this paper, we proposed a ... More

An Investigation On Fuzzy Logic Controllers (TAKAGI-SUGENO & MAMDANI) In Inverse Pendulum SystemAug 22 2013The concept of controlling non-linear systems is one the significant fields in scientific researches for the purpose of which intelligent approaches can provide desirable applicability. Fuzzy systems are systems with ambiguous definition and fuzzy control ... More

Experiential, Distributional and Dependency-based Word Embeddings have Complementary Roles in Decoding Brain ActivityNov 25 2017We evaluate 8 different word embedding models on their usefulness for predicting the neural activation patterns associated with concrete nouns. The models we consider include an experiential model, based on crowd-sourced association data, several popular ... More

Fair Dimensionality Reduction and Iterative Rounding for SDPsFeb 28 2019We model "fair" dimensionality reduction as an optimization problem. A central example is the fair PCA problem: the input data is divided into $k$ groups, and the goal is to find a single $d$-dimensional representation for all groups for which the maximum ... More

Simultaneous Multi Layer Access: A High Bandwidth and Low Cost 3D-Stacked Memory InterfaceJun 10 2015Limited memory bandwidth is a critical bottleneck in modern systems. 3D-stacked DRAM enables higher bandwidth by leveraging wider Through-Silicon-Via (TSV) channels, but today's systems cannot fully exploit them due to the limited internal bandwidth of ... More

Guarantees for Spectral Clustering with Fairness ConstraintsJan 24 2019Given the widespread popularity of spectral clustering (SC) for partitioning graph data, we study a version of constrained SC in which we try to incorporate the fairness notion proposed by Chierichetti et al. (2017). According to this notion, a clustering ... More

Tuning the work function of graphene toward application as anode and cathodeMay 16 2019The rapid technological progress in the 21st century demands new multi-functional materials applicable to a wide variety of industries. Two-dimensional (2D) materials are predicted to have a revolutionary impact on the cost, size, weight, and functions ... More

Comprehensive Analysis of Dynamic Message Sign Impact on Driver Behavior: A Random Forest ApproachMar 10 2019This study investigates the potential effects of different Dynamic Message Signs (DMSs) on driver behavior using a full-scale high-fidelity driving simulator. Different DMSs are categorized by their content, structure, and type of messages. A random forest ... More

A GA-based feature selection of the EEG signals by classification evaluation: Application in BCI systemsJan 16 2019In electroencephalogram (EEG) signal processing, finding the appropriate information from a dataset has been a big challenge for successful signal classification. The feature selection methods make it possible to solve this problem; however, the method ... More

The Price of Fair PCA: One Extra DimensionOct 31 2018We investigate whether the standard dimensionality reduction technique of PCA inadvertently produces data representations with different fidelity for two different populations. We show on several real-world data sets, PCA has higher reconstruction error ... More

Partial Zero-Forcing for Multi-Way Relay NetworksOct 12 2017Apr 19 2018The ever increasing demands for mobile network access have resulted in a significant increase in bandwidth usage. By improving the system spectral efficiency, multi-way relay networks (MWRNs) provide promising approaches to address this challenge. In ... More

Fair Dimensionality Reduction and Iterative Rounding for SDPsFeb 28 2019Jun 18 2019Dimensionality reduction is a classical technique widely used for data analysis. One foundational instantiation is Principal Component Analysis (PCA), which minimizes the average reconstruction error. In this paper, we introduce the "multi-criteria dimensionality ... More

Blackbox meets blackbox: Representational Similarity and Stability Analysis of Neural Language Models and BrainsJun 04 2019In this paper, we define and apply representational stability analysis (ReStA), an intuitive way of analyzing neural language models. ReStA is a variant of the popular representational similarity analysis (RSA) in cognitive neuroscience. While RSA can ... More

Bidirectional Helmholtz MachinesJun 12 2015May 25 2016Efficient unsupervised training and inference in deep generative models remains a challenging problem. One basic approach, called Helmholtz machine, involves training a top-down directed generative model together with a bottom-up auxiliary model used ... More

Blackbox meets blackbox: Representational Similarity and Stability Analysis of Neural Language Models and BrainsJun 04 2019Jun 05 2019In this paper, we define and apply representational stability analysis (ReStA), an intuitive way of analyzing neural language models. ReStA is a variant of the popular representational similarity analysis (RSA) in cognitive neuroscience. While RSA can ... More

A Graph Theory Approach for Regional Controllability of Boolean Cellular AutomataApr 15 2019Controllability is one of the central concepts of modern control theory that allows a good understanding of a system's behaviour. It consists in constraining a system to reach the desired state from an initial state within a given time interval. When ... More

Incremental Reading for Question AnsweringJan 15 2019Any system which performs goal-directed continual learning must not only learn incrementally but process and absorb information incrementally. Such a system also has to understand when its goals have been achieved. In this paper, we consider these issues ... More

Reducing DRAM Latency by Exploiting Design-Induced Latency Variation in Modern DRAM ChipsOct 30 2016Variation has been shown to exist across the cells within a modern DRAM chip. Prior work has studied and exploited several prior forms of this variation, such as manufacturing-process- or temperature-induced variation. We empirically observe a new form ... More

Shrinking Horizon Model Predictive Control with Signal Temporal Logic Constraints under Stochastic DisturbancesMay 05 2017We present Shrinking Horizon Model Predictive Control (SHMPC) for discrete-time linear systems with Signal Temporal Logic (STL) specification constraints under stochastic disturbances. The control objective is to maximize an optimization function under ... More

Towards Deep Conversational RecommendationsDec 18 2018Mar 04 2019There has been growing interest in using neural networks and deep learning techniques to create dialogue systems. Conversational recommendation is an interesting setting for the scientific exploration of dialogue with natural language as the associated ... More

The Spectroscopic Orbits of Five Solar Type, Single Lined BinariesFeb 05 2014We have determined spectroscopic orbits for five single-lined spectroscopic binaries, HD 100167, HD 135991, HD 140667, HD 158222, HD 217924. Their periods range from 60.6 to 2403 days and the eccentricities, from 0.20 to 0.84. Our spectral classes for ... More

Vulnerable to Misinformation? Verifi!Jul 25 2018Mar 17 2019We present Verifi2, a visual analytic system to support the investigation of misinformation on social media. On the one hand, social media platforms empower individuals and organizations by democratizing the sharing of information. On the other hand, ... More

Multiple Microtubule Tracking in Microscopy Time-Lapse Images Using Piecewise-stationary Multiple Motion Model Kalman SmootherJan 11 2019Microtubules are inherently dynamic sub-cellular filamentuous polymers that are spatially organized within the cell by motor proteins which cross-link and move microtubules. In-vitro microtubule motility assays, in which motors attached to a surface move ... More

FigureQA: An Annotated Figure Dataset for Visual ReasoningOct 19 2017Feb 22 2018We introduce FigureQA, a visual reasoning corpus of over one million question-answer pairs grounded in over 100,000 images. The images are synthetic, scientific-style figures from five classes: line plots, dot-line plots, vertical and horizontal bar graphs, ... More

Optimising data for modelling neuronal responsesMay 20 2018In this technical note, we address an unresolved challenge in neuroimaging statistics: how to determine which of several datasets is the best for inferring neuronal responses. Comparisons of this kind are important for experimenters when choosing an imaging ... More

Microtubule Motility Analysis based on Time-Lapse Fluorescence MicroscopyMay 27 2019This paper describes an investigation into part of the mechanical mechanisms underlying the formation of mitotic spindle, the cellular machinery responsible for chromosomal separation during cell division. In normal eukaryotic cells, spindles are composed ... More

FitNets: Hints for Thin Deep NetsDec 19 2014Mar 27 2015While depth tends to improve network performances, it also makes gradient-based training more difficult since deeper networks tend to be more non-linear. The recently proposed knowledge distillation approach is aimed at obtaining small and fast-to-execute ... More

Towards Deep Conversational RecommendationsDec 18 2018There has been growing interest in using neural networks and deep learning techniques to create dialogue systems. Conversational recommendation is an interesting setting for the scientific exploration of dialogue with natural language as the associated ... More

On the Learning Dynamics of Deep Neural NetworksSep 18 2018While a lot of progress has been made in recent years, the dynamics of learning in deep nonlinear neural networks remain to this day largely misunderstood. In this work, we study the case of binary classification and prove various properties of learning ... More

A Simple Form for the Ground State Rotational Band of even-even Actinide nucleiJan 03 2010Feb 24 2010From Bohr-Mottelson model, a three parametric simple expression for the ground state rotational band of deformed even-even nuclei is deduced by incorporating the variable moment of inertia and the softness parameter. Our obtained results show good agreement ... More

ChatPainter: Improving Text to Image Generation using DialogueFeb 22 2018Synthesizing realistic images from text descriptions on a dataset like Microsoft Common Objects in Context (MS COCO), where each image can contain several objects, is a challenging task. Prior work has used text captions to generate images. However, captions ... More

Adaptive-Latency DRAM: Reducing DRAM Latency by Exploiting Timing MarginsMay 04 2018This paper summarizes the idea of Adaptive-Latency DRAM (AL-DRAM), which was published in HPCA 2015, and examines the work's significance and future potential. AL-DRAM is a mechanism that optimizes DRAM latency based on the DRAM module and the operating ... More

Understanding and Exploiting Design-Induced Latency Variation in Modern DRAM ChipsOct 30 2016May 15 2017Variation has been shown to exist across the cells within a modern DRAM chip. We empirically demonstrate a new form of variation that exists within a real DRAM chip, induced by the design and placement of different components in the DRAM chip. Our goals ... More

Adaptive-Latency DRAM (AL-DRAM)Mar 28 2016This paper summarizes the idea of Adaptive-Latency DRAM (AL-DRAM), which was published in HPCA 2015. The key goal of AL-DRAM is to exploit the extra margin that is built into the DRAM timing parameters to reduce DRAM latency. The key observation is that ... More

A Holistic Survey of Wireless Multipath Video StreamingJun 14 2019Most of today's mobile devices are equipped with multiple network interfaces and one of the main bandwidth-hungry applications that would benefit from multipath communications is wireless video streaming. However, most of current transport protocols do ... More

Vulnerable to Misinformation? Verifi!Jul 25 2018We present Verifi2, a visual analytic system to support the investigation of misinformation on social media. On the one hand, social media platforms empower individuals and organizations by democratizing the sharing of information. On the other hand, ... More

ExtremeWeather: A large-scale climate dataset for semi-supervised detection, localization, and understanding of extreme weather eventsDec 07 2016Nov 25 2017Then detection and identification of extreme weather events in large-scale climate simulations is an important problem for risk management, informing governmental policy decisions and advancing our basic understanding of the climate system. Recent work ... More

Instance-Level Microtubule Segmentation Using Recurrent AttentionJan 17 2019We propose a new deep learning algorithm for multiple microtubule (MT) segmentation in time-lapse images using the recurrent attention. Segmentation results from each pair of succeeding frames are being fed into a Hungarian algorithm to assign correspondences ... More

Anchored in a Data Storm: How Anchoring Bias Can Affect User Strategy, Confidence, and Decisions in Visual AnalyticsJun 07 2018Cognitive biases have been shown to lead to faulty decision-making. Recent research has demonstrated that the effect of cognitive biases, anchoring bias in particular, transfers to information visualization and visual analytics. However, it is still unclear ... More

SoftMC: Practical DRAM Characterization Using an FPGA-Based InfrastructureMay 08 2018This paper summarizes the SoftMC DRAM characterization infrastructure, which was published in HPCA 2017, and examines the work's significance and future potential. SoftMC (Soft Memory Controller) is the first publicly-available DRAM testing infrastructure ... More

Do Deep Convolutional Nets Really Need to be Deep (Or Even Convolutional)?Mar 17 2016May 27 2016Yes, apparently they do. Previous research showed that shallow feed-forward nets sometimes can learn the complex functions previously learned by deep nets while using the same number of parameters as the deep models they mimic. In this paper we train ... More

Do Deep Convolutional Nets Really Need to be Deep and Convolutional?Mar 17 2016Nov 04 2016Yes, they do. This paper provides the first empirical demonstration that deep convolutional models really need to be both deep and convolutional, even when trained with methods such as distillation that allow small or shallow models of high accuracy to ... More

Keep Drawing It: Iterative language-based image generation and editingNov 24 2018Conditional text-to-image generation approaches commonly focus on generating a single image in a single step. One practical extension beyond one-step generation is an interactive system that generates an image iteratively, conditioned on ongoing linguistic ... More

Tell, Draw, and Repeat: Generating and modifying images based on continual linguistic instructionNov 24 2018Apr 01 2019Conditional text-to-image generation is an active area of research, with many possible applications. Existing research has primarily focused on generating a single image from available conditioning information in one step. One practical extension beyond ... More

Do Deep Convolutional Nets Really Need to be Deep and Convolutional?Mar 17 2016Mar 04 2017Yes, they do. This paper provides the first empirical demonstration that deep convolutional models really need to be both deep and convolutional, even when trained with methods such as distillation that allow small or shallow models of high accuracy to ... More

Decoupling GPU Programming Models from Resource Management for Enhanced Programming Ease, Portability, and PerformanceMay 02 2018The application resource specification--a static specification of several parameters such as the number of threads and the scratchpad memory usage per thread block--forms a critical component of modern GPU programming models. This specification determines ... More

Zorua: Enhancing Programming Ease, Portability, and Performance in GPUs by Decoupling Programming Models from Resource ManagementFeb 07 2018The application resource specification--a static specification of several parameters such as the number of threads and the scratchpad memory usage per thread block--forms a critical component of the existing GPU programming models. This specification ... More

Aharonov-Bohm effect in grapheneNov 09 2007We investigate experimentally transport through ring-shaped devices etched in graphene and observe clear Aharonov-Bohm conductance oscillations. The temperature dependence of the oscillation amplitude indicates that below 1 K the phase coherence length ... More

Near-infrared excitation of nitrogen-doped ultrananocrystalline diamond photoelectrodes in saline solutionNov 20 2018Nitrogen-doped ultrananocrystalline diamond (N-UNCD) is a promising material for a variety of neural interfacing applications, due to its unique combination of high conductivity, bioinertness, and durability. One emerging application for N-UNCD is as ... More

Spectro-interferometric observations of classical nova V458 Vul 2007Jun 22 2012We used the Palomar Testbed Interferometer (PTI) to resolve 2.2 $\mu$m emission from the classical nova V458 Vul 2007 over the course of several days following its discovery on 2007 August 8.54 UT. We also obtained K-band photometric data and spectra ... More

Influence of Ibuprofen on Phospholipid MembranesJun 13 2014Sep 14 2014Basic understanding of biological membranes is of paramount importance as these membranes comprise the very building blocks of life itself. Cells depend in their function on a range of properties of the membrane, which are important for the stability ... More

Flexible-Latency DRAM: Understanding and Exploiting Latency Variation in Modern DRAM ChipsMay 08 2018This article summarizes key results of our work on experimental characterization and analysis of latency variation and latency-reliability trade-offs in modern DRAM chips, which was published in SIGMETRICS 2016, and examines the work's significance and ... More

The "something something" video database for learning and evaluating visual common senseJun 13 2017Jun 15 2017Neural networks trained on datasets such as ImageNet have led to major advances in visual object classification. One obstacle that prevents networks from reasoning more deeply about complex scenes and situations, and from integrating visual knowledge ... More

EmoNets: Multimodal deep learning approaches for emotion recognition in videoMar 05 2015Mar 30 2015The task of the emotion recognition in the wild (EmotiW) Challenge is to assign one of seven emotions to short video clips extracted from Hollywood style movies. The videos depict acted-out emotions under realistic conditions with a large degree of variation ... More

Theano: A Python framework for fast computation of mathematical expressionsMay 09 2016Theano is a Python library that allows to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. Since its introduction, it has been one of the most used CPU and GPU mathematical compilers - especially ... More