Searcharxiv⌕ Search

arXiv subjects

Kuldeep Singh

Publications and source records attributed to Kuldeep Singh.

59 records · Page 4Linked to original sources

Self-Attention: A Better Building Block for Sentiment Analysis Neural Network Classifiers

Sentiment Analysis has seen much progress in the past two decades. For the past few years, neural network approaches, primarily RNNs and CNNs, have been the most successful for this task. Recently, a new category of neural networks, self-attention networks (SANs), have been created which utilizes the attention mechanism as the basic building block. Self-attention networks have been shown to be effective for sequence modeling tasks, while having no recurrence or convolutions. In this work we explore the effectiveness of the SANs for sentiment analysis. We demonstrate that SANs are superior in performance to their RNN and CNN counterparts by comparing their classification accuracy on six datasets as well as their model characteristics such as training speed and memory consumption. Finally, we explore the effects of various SAN modifications such as multi-head attention as well as two methods of incorporating sequence position information into SANs.

cs.CL↗

Robust Object Tracking with Crow Search Optimized Multi-cue Particle Filter

Particle Filter(PF) is used extensively for estimation of target Non-linear and Non-gaussian state. However, its performance suffers due to inherent problem of sample degeneracy and impoverishment. In order to address this, we propose a novel resampling method based upon Crow Search Optimization to overcome low performing particles detected as outlier. Proposed outlier detection mechanism with transductive reliability achieve faster convergence of proposed PF tracking framework. In addition, we present an adaptive fuzzy fusion model to integrate multi-cue extracted for each evaluated particle. Automatic boosting and suppression of particles using proposed fusion model not only enhances performance of resampling method but also achieve optimal state estimation. Performance of the proposed tracker is evaluated over 12 benchmark video sequences and compared with state-of-the-art solutions. Qualitative and quantitative results reveals that the proposed tracker not only outperforms existing solutions but also efficiently handle various tracking challenges. On average of outcome, we achieve CLE of 7.98 and F-measure of 0.734.

cs.CV↗

Study of Magnetized accretion flow with cooling processes

We have studied shock in magnetized accretion flow/funnel flow in case of neutron star with bremsstrahlung cooling and cyclotron cooling. All accretion solutions terminate with a shock close to the neutron star surface, but at some region of the parameter space, it also harbours a second shock away from the star surface. We have found that cyclotron cooling is necessary for correct accretion solutions which match the surface boundary conditions.

astro-ph.HE↗

Study of magnetized accretion flow with variable $Γ$ equation of state

We present here the solutions of magnetized accretion flows on to a compact object with hard surface such as neutron stars. The magnetic field of the central star is assumed dipolar and the magnetic axis is assumed to be aligned with the rotation axis of the star. We have used an equation of state for the accreting fluid in which the adiabatic index is dependent on temperature and composition of the flow. We have also included cooling processes like bremsstrahlung and cyclotron processes in the accretion flow. We found all possible accretion solutions. All accretion solutions terminate with a shock very near to the star surface and the height of this primary shock do not vary much with either the spin period or the Bernoulli parameter of the flow, although the strength of the shock may vary with the period. For moderately rotating central star there are possible formation of multiple sonic points in the flow and therefore, a second shock far away from the star surface may also form. However, the second shock is much weaker than the primary one near the surface. We found that if rotation period is below a certain value $(\pmin)$, then multiple critical points or multiple shocks are not possible and $\pmin$ depends upon the composition of the flow. We also found that cooling effect dominates after the shock and that the cyclotron and the bremsstrahlung cooling processes should be considered to obtain a consistent accretion solution.

astro-ph.HE↗

Question Answering on Linked Data: Challenges and Future Directions

Question Answering (QA) systems are becoming the inspiring model for the future of search engines. While recently, underlying datasets for QA systems have been promoted from unstructured datasets to structured datasets with highly semantic-enriched metadata, but still question answering systems involve serious challenges which cause to be far beyond desired expectations. In this paper, we raise the challenges for building a Question Answering (QA) system especially with the focus of employing structured data (i.e. knowledge graph). This paper provide an exhaustive insight of the known challenges, so far. Thus, it helps researchers to easily spot open rooms for the future research agenda.

cs.IR↗