Results for "Puneet K. Dokania"

total 87688took 0.23s
Stable Rank Normalization for Improved Generalization in Neural Networks and GANsJun 11 2019Jun 12 2019Exciting new work on the generalization bounds for neural networks (NN) given by Neyshabur et al. , Bartlett et al. closely depend on two parameter-depenedent quantities: the Lipschitz constant upper-bound and the stable rank (a softer version of the ... More
Parsimonious LabelingJul 05 2015We propose a new family of discrete energy minimization problems, which we call parsimonious labeling. Specifically, our energy functional consists of unary potentials and high-order clique potentials. While the unary potentials are arbitrary, the clique ... More
Deformable Registration through Learning of Context-Specific Metric AggregationJul 19 2017We propose a novel weakly supervised discriminative algorithm for learning context specific registration metrics as a linear combination of conventional similarity measures. Conventional metrics have been extensively used over the past two decades and ... More
Weakly-Supervised Learning of Metric Aggregations for Deformable Image RegistrationSep 24 2018Deformable registration has been one of the pillars of biomedical image computing. Conventional approaches refer to the definition of a similarity criterion that, once endowed with a deformation model and a smoothness constraint, determines the optimal ... More
Stable Rank Normalization for Improved Generalization in Neural Networks and GANsJun 11 2019Exciting new work on the generalization bounds for neural networks (NN) given by Neyshabur et al. , Bartlett et al. depend on two parameter-depenedent quantities: the Lipschitz constant upper-bound and the stable rank (a softer version of the rank operator). ... More
Induced Dynamics on the HyperspacesDec 22 2015Mar 10 2016In this paper, we study the dynamics induced by finite commutative relation. We prove that the dynamics generated by such a non-trivial collection cannot be transitive/super-transitive and hence cannot exhibit higher degrees of mixing. As a consequence ... More
Proximal Mean-field for Neural Network QuantizationDec 11 2018Compressing large neural networks by quantizing the parameters, while maintaining the performance is often highly desirable due to the reduced memory and time complexity. In this work, we formulate neural network quantization as a discrete labelling problem ... More
Proximal Mean-field for Neural Network QuantizationDec 11 2018Apr 26 2019Compressing large Neural Networks (NN) by quantizing the parameters, while maintaining the performance is highly desirable due to reduced memory and time complexity. In this work, we cast NN quantization as a discrete labelling problem and leverage results ... More
Visual Dialogue without Vision or DialogueDec 16 2018We characterise some of the quirks and shortcomings in the exploration of Visual Dialogue (VD) - a sequential question-answering task where the questions and corresponding answers are related through given visual stimuli. To do so, we develop an embarrassingly ... More
FlipDial: A Generative Model for Two-Way Visual DialogueFeb 11 2018Apr 03 2018We present FlipDial, a generative model for visual dialogue that simultaneously plays the role of both participants in a visually-grounded dialogue. Given context in the form of an image and an associated caption summarising the contents of the image, ... More
Visual Dialogue without Vision or DialogueDec 16 2018Feb 26 2019We characterise some of the quirks and shortcomings in the exploration of Visual Dialogue - a sequential question-answering task where the questions and corresponding answers are related through given visual stimuli. To do so, we develop an embarrassingly ... More
Minding the Gaps for Block Frank-Wolfe Optimization of Structured SVMsMay 30 2016In this paper, we propose several improvements on the block-coordinate Frank-Wolfe (BCFW) algorithm from Lacoste-Julien et al. (2013) recently used to optimize the structured support vector machine (SSVM) objective in the context of structured prediction, ... More
Matrix Characterization of Multidimensional Subshifts of Finite TypeMar 02 2016Let $X\subset A^{Z^d}$ be a $2$-dimensional subshift of finite type. We prove that any $2$-dimensional multidimensional subshift of finite type can be characterized by a square matrix of infinite dimension. We extend our result to a general $d$-dimensional ... More
On Tiny Episodic Memories in Continual LearningFeb 27 2019Jun 04 2019In continual learning (CL), an agent learns from a stream of tasks leveraging prior experience to transfer knowledge to future tasks. It is an ideal framework to decrease the amount of supervision in the existing learning algorithms. But for a successful ... More
Inferring gender of a Twitter user using celebrities it followsMay 26 2014This paper addresses the task of user gender classification in social media, with an application to Twitter. The approach automatically predicts gender by leveraging observable information such as the tweet behavior, linguistic content of the user's Twitter ... More
Continual Learning with Tiny Episodic MemoriesFeb 27 2019Learning with less supervision is a major challenge in artificial intelligence. One sensible approach to decrease the amount of supervision is to leverage prior experience and transfer knowledge from tasks seen in the past. However, a necessary condition ... More
Continual Learning with Tiny Episodic MemoriesFeb 27 2019Mar 20 2019Learning with less supervision is a major challenge in artificial intelligence. One sensible approach to decrease the amount of supervision is to leverage prior experience and transfer knowledge from tasks seen in the past. However, a necessary condition ... More
Alterations And Rearrangements Of A Non-Autonomous Dynamical SystemNov 23 2017Dec 05 2017In this paper, we discuss the dynamics of alterations and rearrangements of a non-autonomous dynamical system generated by the family $\mathbb{F}$. We prove that while insertion/deletion of a map in the family $\mathbb{F}$ can disturb the dynamics of ... More
Giant Dipole Resonance studies in Ba isotopes at $\textbf{ E/A}\sim$ 5 MeVApr 17 2017Apr 18 2017Exclusive measurements of high energy $\gamma$-rays are performed in $\rm ^{124}Ba$ and $\rm ^{136}Ba$ at the same excitation energy ($\sim$ 49 MeV), to study properties of the giant dipole resonance (GDR) over a wider $N/Z$ range. The high energy $\gamma$-rays ... More
Thermal Conduction in one dimensional $Φ^4$ chains with colliding particlesJun 24 2019Studying thermal conduction in low-dimensional non-integrable systems is necessary for understanding the microscopic origin of macroscopic irreversible behavior and Fourier's law of heat conduction. Two distinct types of low-dimensional thermal conduction ... More
Planning and Optimization of Wireless LANs through Field MeasurementsSep 02 2013In this paper, the field measurements of signal strength taken at the frequency of 2432 MHz in indoor & outdoor environments are presented and analyzed. The received signal levels from the base station were monitored manually. Total coverage area considered ... More
Mining Pixels: Weakly Supervised Semantic Segmentation Using Image LabelsDec 07 2016We consider the task of learning a classifier for semantic segmentation using weak supervision, in this case, image labels specifying the objects within the image. Our method uses deep convolutional neural networks (CNNs) and adopts an Expectation-Maximization ... More
A short visit into the Dehn filling TheoryMay 15 2006May 17 2006This article was withdrawn by the arXiv.org administrators since it plagiarizes math.GT/0011056.
Bottom-Up Top-Down Cues for Weakly-Supervised Semantic SegmentationDec 07 2016Apr 09 2017We consider the task of learning a classifier for semantic segmentation using weak supervision in the form of image labels which specify the object classes present in the image. Our method uses deep convolutional neural networks (CNNs) and adopts an Expectation-Maximization ... More
Characterization and modeling of a low background HPGe detectorNov 19 2013Jan 23 2014A high efficiency, low background counting setup has been made at TIFR consisting of a special HPGe detector ($\sim$ 70%) surrounded by a low activity copper+lead shield. Detailed measurements are performed with point and extended geometry sources to ... More
Computer Aided Design Modeling for Heterogeneous ObjectsApr 20 2010Heterogeneous object design is an active research area in recent years. The conventional CAD modeling approaches only provide geometry and topology of the object, but do not contain any information with regard to the materials of the object and so can ... More
LSTM-based Encoder-Decoder for Multi-sensor Anomaly DetectionJul 01 2016Jul 11 2016Mechanical devices such as engines, vehicles, aircrafts, etc., are typically instrumented with numerous sensors to capture the behavior and health of the machine. However, there are often external factors or variables which are not captured by sensors ... More
Quantum scale anomaly and spatial coherence in a 2D Fermi superfluidMay 12 2018Quantum anomalies are violations of classical scaling symmetries caused by quantum fluctuations. Although they appear prominently in quantum field theory to regularize divergent physical quantities, their influence on experimental observables is difficult ... More
Induced Dynamics of Non-Autonomous Discrete Dynamical SystemsMar 17 2017In this paper, we investigate the dynamics on the hyperspace induced by a non-autonomous dynamical system $(X,\mathbb{F})$, where the non-autonomous system is generated by a sequence $(f_n)$ of continuous self maps on $X$. We relate the dynamical behavior ... More
Estimation of low energy neutron flux ($E_n\leq15$ MeV) in India-based Neutrino Observatory cavern using Monte Carlo techniquesSep 23 2015Jan 13 2016The neutron flux at low energy ($E_n\leq15$ MeV) resulting from the radioactivity of the rock in the underground cavern of the India-based Neutrino Observatory is estimated using Geant4-based Monte Carlo simulations. The neutron production rate due to ... More
Study of Radioactive Impurities in Neutron Transmutation Doped GermaniumJun 06 2014Nov 27 2014A program to develop low temperature (mK) sensors with neutron transmutation doped Ge for rare event studies with a cryogenic bolometer has been initiated. For this purpose, semiconductor grade Ge wafers are irradiated with thermal neutron flux from Dhruva ... More
Study of neutron-induced background and its effect on the search of 0$νββ$ decay in $\rm^{124}Sn$Aug 21 2014Oct 04 2014Neutron-induced background has been studied in various components of the TIN.TIN detector, which is under development for the search of Neutrinoless Double Beta Decay in $\rm^{124}Sn$. Fast neutron flux $\sim10^{6}~n~cm^{-2}s^{-1}$ covering a broad energy ... More
The Supersymmetric HiggsSep 22 2008In the Minimal Supersymmetric Standard Model (the MSSM), the electroweak symmetry is restored as supersymmetry-breaking terms are turned off. We describe a generic extension of the MSSM where the electroweak symmetry is broken in the supersymmetric limit. ... More
A Conceptual E-Governance Framework for Improving Child Immunization Process in IndiaMay 17 2013India is country having high population and great variations in the educational level, economic conditions, population densities, cultures and awareness levels. Due to these variations the immunization process is not so much successful as per expectations ... More
Transitions Between de Sitter MinimaDec 11 2006Jun 28 2007We investigate the cosmological signatures of instantons mediating tunneling between de Sitter minima. For generic potentials the Coleman-de Luccia instanton does not necessarily exist; when it does not, the instanton which contributes to the decay rate ... More
Dynamics of the Induced Shift MapFeb 09 2017Feb 13 2017In this article, we compare the dynamics of the shift map and its induced counterpart on the hyperspace of the shift space. We show that many of the properties of induced shift map can be easily demonstrated by appropriate sequences of symbols. We compare ... More
Dynamics of Nonautonomous Discrete Dynamical SystemsDec 30 2015Jan 19 2016In this paper we study the dynamics of a general non-autonomous dynamical system generated by a family of continuous self maps on a compact space $X$. We derive necessary and sufficient conditions for the system to exhibit complex dynamical behavior. ... More
Deep Neural Networks in High Frequency TradingSep 05 2018Oct 29 2018The ability to give precise and fast prediction for the price movement of stocks is the key to profitability in High Frequency Trading. The main objective of this paper is to propose a novel way of modeling the high frequency trading problem using Deep ... More
Two-dimensional time-reversible ergodic maps with provisions for dissipationNov 13 2015Dec 31 2015A new discrete time-reversible map of a unit square onto itself is proposed. The map comprises of piecewise linear two-dimensional operations, and is able to represent the macroscopic features of both equilibrium and nonequilibrium dynamical systems. ... More
Multidimensional Shifts And Finite MatricesJan 21 2019Feb 05 2019Let $X$ be a $2$-dimensional subshift of finite type generated by a finite set of forbidden blocks (of finite size). We give an algorithm for generating the elements of the shift space using sequence of finite matrices (of increasing size). We prove that ... More
Dynamics Of Finitely Generated Non-Autonomous SystemsOct 02 2018In this paper, we discuss dynamical behavior of a non-autonomous system generated by a finite family $\mathbb{F}$. In the process, we relate the dynamical behavior of the non-autonomous system generated by the family $\mathbb{F}=\{f_1,f_2,\ldots,f_k\}$ ... More
Hotspot-aware DSA Grouping and Mask AssignmentOct 09 2017In Directed Self Assembly (DSA), poor printing of guiding templates can cause misassembly resulting in high defect probability. Therefore, hotspots should be avoided in the choice of the DSA groups. Accordingly, Directed Self-Assembly (DSA) technologies ... More
On Dynamics Generated by a Uniformly Convergent Sequence of MapsMar 20 2017Sep 29 2017In this paper, we study the dynamics of a non-autonomous dynamical system $(X,\mathbb{F})$ generated by a sequence $(f_n)$ of continuous self maps converging uniformly to $f$. We relate the dynamics of the non-autonomous system $(X,\mathbb{F})$ with the ... More
A Composite Twin Higgs ModelNov 03 2008Twin Higgs models are economical extensions of the Standard Model that stabilize the electroweak scale. In these theories the Higgs field is a pseudo Nambu-Goldstone boson that is protected against radiative corrections up to scales of order 5 TeV by ... More
Symmetry Breaking Patterns for the Little Higgs from Strong DynamicsOct 01 2007We show how the symmetry breaking pattern of the simplest little Higgs model, and that of the smallest moose model that incorporates an approximate custodial SU(2), can be realized through the condensation of strongly coupled fermions. In each case a ... More
Analysis of SQL Injection Detection TechniquesMay 09 2016SQL Injection is one of the vulnerabilities in OWASPs Top Ten List for Web Based Application Exploitation.These types of attacks takes place on Dynamic Web applications as they interact with the databases for the various operations.Current Content Management ... More
Radiation Background Studies for 0$νββ$ decay in $^{124}$SnApr 21 2015Radiation background studies pertaining to $0\nu\beta\beta$ decay in $^{124}$Sn have been carried out. A TiLES setup has been installed at TIFR for this purpose. Neutron-induced background is studied in the TIN.TIN detector materials using fast neutron ... More
Perturbative, Non-Supersymmetric Completions of the Little HiggsDec 20 2004The little Higgs mechanism produces a light 100 GeV Higgs while raising the natural cutoff from 1 TeV to 10 TeV. We attempt an iterative little Higgs mechanism to produce multiple factors of 10 between the cutoff and the 100 GeV Higgs mass in a perturbative ... More
Non-Ergodicity of Nose-Hoover chain thermostat in computationally achievable timeJul 09 2014The widely used Nose-Hoover chain (NHC) thermostat in molecular dynamics simulations is generally believed to impart the canonical distribution as well as quasi- (i.e., space filling) ergodicity on the thermostatted physical system (PS). Working with ... More
Comparative Advantage Driven Resource Allocation for Virtual Network FunctionsMar 12 2016As Communication Service Providers (CSPs) adopt the Network Function Virtualization (NFV) paradigm, they need to transition their network function capacity to a virtualized infrastructure with different Network Functions running on a set of heterogeneous ... More
Equilibrium free energy differences at different temperatures from a single set of nonequilibrium transitionsMar 26 2015Jan 14 2017Crook's Fluctuation Theorem and Jarzynski equality are immensely powerful tools in obtaining equilibrium properties through non-equilibrium transition between two equilibrium states. In this letter, we propose an extension to the Crook's fluctuation theorem ... More
Improving the ergodic characteristics of thermostats using higher order temperaturesNov 09 2014Most deterministic schemes for controlling temperature by kinetic variables (NH thermsotat), configurational variables (BT thermostat) and all phase space variables (PB thermostat) are non-ergodic for systems with a few degrees of freedom. While for the ... More
Heat pump without particle transport or external work on the medium achieved by differential thermostatting of the phase spaceMar 28 2016We propose a new mechanism that enables heat flow from a colder region to a hotter region without necessitating either particle transport or external work on the conductor, thereby bypassing the compressor part of a classical heat pump cycle. Our mechanism ... More
A Determination of the Hubble Constant from Cepheid Distances and a Model of the Local Peculiar Velocity FieldMay 06 2000Feb 28 2001We present a measurement of the Hubble Constant based on Cepheid distances to 27 galaxies within 20 Mpc. We take the Cepheid data from published measurements by the Hubble Telescope Key Project on the Distance Scale (H0KP). We calibrate the Cepheid Period-Luminosity ... More
Equilibrium free energy differences at different temperatures from a single set of nonequilibrium transitionsMar 26 2015Crook's Fluctuation Theorem and Jarzynski equality are immensely powerful tools in obtaining equilibrium properties through non-equilibrium transition between two equilibrium states. In this letter, we propose an extension to the Crook's fluctuation theorem ... More
New limit for the half-life of double beta decay of $^{94}$Zr to the first excited state of $^{94}$MoAug 08 2016Aug 11 2016Double Beta Decay is a phenomenon of fundamental interest for particle physics and the study of these transitions to the excited states is of relevance to the calculation of Nuclear Transition Matrix Element for the process. In the present work, double ... More
Opportunistic Self Organizing Migrating Algorithm for Real-Time Dynamic Traveling Salesman ProblemSep 12 2017Self Organizing Migrating Algorithm (SOMA) is a meta-heuristic algorithm based on the self-organizing behavior of individuals in a simulated social environment. SOMA performs iterative computations on a population of potential solutions in the given search ... More
New limit for the half-life of double beta decay of $^{94}$Zr to the first excited state of $^{94}$MoAug 08 2016Mar 31 2017Neutrinoless Double Beta Decay is a phenomenon of fundamental interest in particle physics. The decay rates of double beta decay transitions to the excited states can provide input for Nuclear Transition Matrix Element calculations for the relevant two ... More
Distributed Approximation Algorithms for the Combinatorial Motion Planning ProblemMay 23 2018We present a new $4$-approximation algorithm for the Combinatorial Motion Planning problem which runs in $\mathcal{O}(n^2\alpha(n^2,n))$ time, where $\alpha$ is the functional inverse of the Ackermann function, and a fully distributed version for the ... More
Characterization of neutron transmutation doped (NTD) Ge for low temperature sensor developmentOct 15 2014Dec 05 2014Development of NTD Ge sensors has been initiated for low temperature (mK) thermometry in The India-based Tin detector (TIN.TIN). NTD Ge sensors are prepared by thermal neutron irradiation of device grade Ge samples at Dhruva reactor, BARC, Mumbai. Detailed ... More
Policy Aware Geospatial DataApr 21 2013Digital Rights Management (DRM) prevents end-users from using content in a manner inconsistent with its creator's wishes. The license describing these use-conditions typically accompanies the content as its metadata. A resulting problem is that the license ... More
Approximating the entire spectrum of nonequilibrium steady state distributions using relative entropy: An application to thermal conductionSep 22 2014We show that distribution functions of nonequilibrium steady states (NESS) evolving under a slowly varying protocol can be accurately obtained from limited data and the closest known detailed state of the system. In this manner, one needs to perform only ... More
Affine Almost Automorphic Actions on Compact NilmanifoldsDec 07 2012We discuss conditions under which an affine automorphism of a compact nilmanifold is almost automorphic, and the structure of such automorphisms from a dynamical point of view.
Narrative Science Systems: A ReviewOct 15 2015Automatic narration of events and entities is the need of the hour, especially when live reporting is critical and volume of information to be narrated is huge. This paper discusses the challenges in this context, along with the algorithms used to build ... More
Measuring the W-t-b Interaction at the ILCJun 06 2006The large top quark mass suggests that the top plays a pivotal role in Electroweak symmetry-breaking dynamics and, as a result, may have modified couplings to Electroweak bosons. Hadron colliders can provide measurements of these couplings at the ~10% ... More
Spontaneous spinning of a rattleback placed on vibrating platformApr 22 2018The spontaneous spinning of a rattleback placed on a vibrating platform is investigated. The rattleback is a toy with some curious properties. When placed on a surface with reasonable friction, the rattleback has a preferred direction of spin. If rotated ... More
Improved Service Delivery and Cost Effective Framework for e-Governance in IndiaJul 29 2013In current era, the involvement of technologies like virtualization, consolidation and cloud computing, and adoption of free and open source software in designing and deploying e-governance that can reduce the total cost associated with and hence the ... More
E-Governance in India: Definitions, Challenges and SolutionsNov 07 2014The Government of India is transcending from traditional modus operandi of governance towards technological involvement in the process of governance. Currently, the Government of India is in the transition phase and seamlessly unleashing the power of ... More
Emulating Human Conversations using Convolutional Neural Network-based IRJun 22 2016Conversational agents ("bots") are beginning to be widely used in conversational interfaces. To design a system that is capable of emulating human-like interactions, a conversational layer that can serve as a fabric for chat-like interaction with the ... More
Anomaly-Free Sets of FermionsOct 13 2005We present new techniques for finding anomaly-free sets of fermions. Although the anomaly cancellation conditions typically include cubic equations with integer variables that cannot be solved in general, we prove by construction that any chiral set of ... More
Relationship Queries on Large graphs using PregelApr 30 2016Large-scale graph-structured data arising from social networks, databases, knowledge bases, web graphs, etc. is now available for analysis and mining. Graph-mining often involves 'relationship queries', which seek a ranked list of interesting interconnections ... More
Horizons in 2+1-dimensional collapse of particlesJul 12 2007A simple, geometrical construction is given for three-dimensional spacetimes with negative cosmological constant that contain two particles colliding head-on. Depending on parameters like particle masses and distance, the combined geometry will the that ... More
Incremental Entity Resolution from Linked DocumentsFeb 18 2014In many government applications we often find that information about entities, such as persons, are available in disparate data sources such as passports, driving licences, bank accounts, and income tax records. Similar scenarios are commonplace in large ... More
Warranty Cost Estimation Using Bayesian NetworkNov 11 2014All multi-component product manufacturing companies face the problem of warranty cost estimation. Failure rate analysis of components plays a key role in this problem. Data source used for failure rate analysis has traditionally been past failure data ... More
ICT in Local Self Governance: A Study of Rural IndiaJan 03 2014The concept of local self-governance is not new as it has its roots in ancient time even before the era of Mauryan emperors. This paper depicts the journey of local self-governance from antediluvian time to 21st century. Further, in the current scenario ... More
Efficient Image Retargeting for High Dynamic Range ScenesMay 20 2013Most of the real world scenes have a very high dynamic range (HDR). The mobile phone cameras and the digital cameras available in markets are limited in their capability in both the range and spatial resolution. Same argument can be posed about the limited ... More
Multi-Sensor Event Detection using Shape HistogramsAug 16 2014Vehicular sensor data consists of multiple time-series arising from a number of sensors. Using such multi-sensor data we would like to detect occurrences of specific events that vehicles encounter, e.g., corresponding to particular maneuvers that a vehicle ... More
Hierarchy Influenced Differential Evolution: A Motor Operation Inspired ApproachFeb 17 2017Sep 12 2017Operational maturity of biological control systems have fuelled the inspiration for a large number of mathematical and logical models for control, automation and optimisation. The human brain represents the most sophisticated control architecture known ... More
Measurement of the $ν_μ$ charged-current cross sections on water, hydrocarbon, iron, and their ratios with the T2K on-axis detectorsApr 21 2019We report a measurement of the flux-integrated $\nu_{\mu}$ charged-current cross sections on water, hydrocarbon, and iron in the T2K on-axis neutrino beam with a mean neutrino energy of 1.5 GeV. The measured cross sections on water, hydrocarbon, and iron ... More
Search for heavy neutrinos with the T2K near detector ND280Feb 20 2019This paper reports on the search for heavy neutrinos with masses in the range $140 < M_N < 493$ MeV/c$^2$ using the off-axis near detector ND280 of the T2K experiment. These particles can be produced from kaon decays in the standard neutrino beam and ... More
Search for CP violation in Neutrino and Antineutrino Oscillations by the T2K experiment with $2.2\times10^{21}$ protons on targetJul 20 2018Sep 22 2018The T2K experiment measures muon neutrino disappearance and electron neutrino appearance in accelerator-produced neutrino and antineutrino beams. With an exposure of $14.7(7.6)\times 10^{20}$ protons on target in neutrino (antineutrino) mode, 89 $\nu_e$ ... More
Search for light sterile neutrinos with the T2K far detector Super-Kamiokande at a baseline of 295 kmFeb 18 2019Jun 05 2019We perform a search for light sterile neutrinos using the data from the T2K far detector at a baseline of 295 km, with an exposure of 14.7 (7.6)$\times 10^{20}$ protons on target in neutrino (antineutrino) mode. A selection of neutral current interaction ... More
Generation of Near-Optimal Solutions Using ILP-Guided SamplingAug 03 2016Our interest in this paper is in optimisation problems that are intractable to solve by direct numerical optimisation, but nevertheless have significant amounts of relevant domain-specific knowledge. The category of heuristic search techniques known as ... More
Architecture for Automated Tagging and Clustering of Song Files According to MoodJun 12 2012Music is one of the basic human needs for recreation and entertainment. As song files are digitalized now a days, and digital libraries are expanding continuously, which makes it difficult to recall a song. Thus need of a new classification system other ... More
A Sentiment-and-Semantics-Based Approach for Emotion Detection in Textual ConversationsJul 21 2017Mar 30 2018Emotions are physiological states generated in humans in reaction to internal or external events. They are complex and studied across numerous fields including computer science. As humans, on reading "Why don't you ever text me!" we can either interpret ... More
One-dimensional surface states on a striped Ag thin film with stacking fault arraysJul 20 2011One-dimensional (1D) stripe structures with a periodicity of 1.3 nm are formed by introduction of stacking fault arrays into a Ag thin film. The surface states of such striped Ag thin films are studied using a low temperature scanning tunneling microscope. ... More
Anomaly Detection in Clutter using Spectrally Enhanced LadarFeb 17 2016Discrete return (DR) Laser Detection and Ranging (Ladar) systems provide a series of echoes that reflect from objects in a scene. These can be first, last or multi-echo returns. In contrast, Full-Waveform (FW)-Ladar systems measure the intensity of light ... More
Approximate Propagation of both Epistemic and Aleatory Uncertainty through Dynamic SystemsJul 08 2011When ignorance due to the lack of knowledge, modeled as epistemic uncertainty using Dempster-Shafer structures on closed intervals, is present in the model parameters, a new uncertainty propagation method is necessary to propagate both aleatory and epistemic ... More
Ergodic Time-Reversible Chaos for Gibbs' Canonical OscillatorMar 23 2015Oct 18 2015Nos\'e's pioneering 1984 work inspired a variety of time-reversible deterministic thermostats. Though several groups have developed successful doubly-thermostated models, single-thermostat models have failed to generate Gibbs' canonical distribution for ... More
Macroscopic Superconducting Current through a Silicon Surface Reconstruction with Indium Adatoms: Si(111)-(R7$\times$R3)-InJul 20 2011Aug 05 2011Macroscopic and robust supercurrents are observed by direct electron transport measurements on a silicon surface reconstruction with In adatoms (Si(111)-(R7xR3)-In). The superconducting transition manifests itself as an emergence of the zero resistance ... More
MEETING BOT: Reinforcement Learning for Dialogue Based Meeting SchedulingDec 28 2018In this paper we present Meeting Bot, a reinforcement learning based conversational system that interacts with multiple users to schedule meetings. The system is able to interpret user utterences and map them to preferred time slots, which are then fed ... More
Characterization of PARIS LaBr$_3$(Ce)-NaI(Tl) phoswich detectors upto $E_γ$ $\sim$ 22 MeVMay 03 2016May 20 2016In order to understand the performance of the PARIS (Photon Array for the studies with Radioactive Ion and Stable beams) detector, detailed characterization of two individual phoswich (LaBr$_3$(Ce)-NaI(Tl)) elements has been carried out. The detector ... More
Approximate Interval Method for Epistemic Uncertainty Propagation using Polynomial Chaos and Evidence TheoryJul 08 2011The paper builds upon a recent approach to find the approximate bounds of a real function using Polynomial Chaos expansions. Given a function of random variables with compact support probability distributions, the intuition is to quantify the uncertainty ... More
Pseudo-redundant vacuum energyJan 29 2008Aug 26 2008We discuss models that can account for today's dark energy. The underlying cosmological constant may be Planck scale but starts as a redundant coupling which can be eliminated by a field redefinition. The observed vacuum energy arises when the redundancy ... More
Deterministic Time-Reversible Thermostats : Chaos, Ergodicity, and the Zeroth Law of ThermodynamicsJan 16 2015The relative stability and ergodicity of deterministic time-reversible thermostats, both singly and in coupled pairs, are assessed through their Lyapunov spectra. Five types of thermostat are coupled to one another through a single Hooke's-Law harmonic ... More
TimeNet: Pre-trained deep recurrent neural network for time series classificationJun 23 2017Inspired by the tremendous success of deep Convolutional Neural Networks as generic feature extractors for images, we propose TimeNet: a deep recurrent neural network (RNN) trained on diverse time series in an unsupervised manner using sequence to sequence ... More
Application of laser biospeckle analysis for assessment of seed priming techniquesNov 01 2018Seed priming is one of the well-established and low cost method to improve seed germination properties, productivity, and stress tolerance in different crops. It is a pre-germination treatment that partially hydrates the seed and allows controlled imbibition. ... More
Decision Based Uncertainty Propagation Using Adaptive Gaussian MixturesJul 08 2011Given a decision process based on the approximate probability density function returned by a data assimilation algorithm, an interaction level between the decision making level and the data assimilation level is designed to incorporate the information ... More
Generation of Near-Optimal Solutions Using ILP-Guided SamplingAug 03 2016Nov 11 2016Our interest in this paper is in optimisation problems that are intractable to solve by direct numerical optimisation, but nevertheless have significant amounts of relevant domain-specific knowledge. The category of heuristic search techniques known as ... More
Deep Convolutional Neural Networks for Pairwise CausalityJan 03 2017Discovering causal models from observational and interventional data is an important first step preceding what-if analysis or counterfactual reasoning. As has been shown before, the direction of pairwise causal relations can, under certain conditions, ... More