arXiv subjects

K. K. Shukla

Publications and source records attributed to K. K. Shukla.

5 recordsLinked to original sources

arXiv2021

Privacy-preserving Machine Learning for Medical Image Classification

With the rising use of Machine Learning (ML) and Deep Learning (DL) in various industries, the medical industry is also not far behind. A very simple yet extremely important use case of ML in this industry is for image classification. This is important for doctors to help them detect certain diseases timely, thereby acting as an aid to reduce chances of human judgement error. However, when using automated systems like these, there is a privacy concern as well. Attackers should not be able to get access to the medical records and images of the patients. It is also required that the model be secure, and that the data that is sent to the model and the predictions that are received both should not be revealed to the model in clear text. In this study, we aim to solve these problems in the context of a medical image classification problem of detection of pneumonia by examining chest x-ray images.

cs.LG↗

arXiv2020

Understanding Interpretability by generalized distillation in Supervised Classification

The ability to interpret decisions taken by Machine Learning (ML) models is fundamental to encourage trust and reliability in different practical applications. Recent interpretation strategies focus on human understanding of the underlying decision mechanisms of the complex ML models. However, these strategies are restricted by the subjective biases of humans. To dissociate from such human biases, we propose an interpretation-by-distillation formulation that is defined relative to other ML models. We generalize the distillation technique for quantifying interpretability, using an information-theoretic perspective, removing the role of ground-truth from the definition of interpretability. Our work defines the entropy of supervised classification models, providing bounds on the entropy of Piece-Wise Linear Neural Networks (PWLNs), along with the first theoretical bounds on the interpretability of PWLNs. We evaluate our proposed framework on the MNIST, Fashion-MNIST and Stanford40 datasets and demonstrate the applicability of the proposed theoretical framework in different supervised classification scenarios.

cs.LG↗

arXiv2019

Globalized Robust Markov Perfect Equilibrium for Discounted Stochastic Games and its Application on Intrusion Detection in Wireless Sensor Networks: Part I -- Theory

In this article, we study a discounted stochastic game to model resource optimal intrusion detection in wireless sensor networks. To address the problem of uncertainties in various network parameters, we propose a globalized robust game theoretic framework for discounted robust stochastic games. A robust solution to the considered problem is an optimal point that is feasible for all realizations of data from a given uncertainty set. To allow a controlled violation of the constraints when the parameters move out of the uncertainty set, the concept of globalized robust framework comes into view. In this article, we formulate a globalized robust counterpart for the discounted stochastic game under consideration. With the help of globalized robust optimization, a concept of globalized robust Markov perfect equilibrium is introduced. The existence of such an equilibrium is shown for a discounted stochastic game when the number of actions of the players is finite. The contraction mapping theorem, Kakutani fixed point theorem and the concept of equicontinuity are used to prove the existence result. To compute a globalized robust Markov perfect equilibrium for the considered discounted stochastic game, a tractable representation of the proposed globalized robust counterpart is also provided. Using the derived tractable representation, we formulate a globalized robust intrusion detection system for wireless sensor networks. The simulation result reveals that the proposed globalized solution is much less sensitive to data perturbations than the robust solution.

cs.GT↗

arXiv2014

Effect of Zn doping on the Magneto-Caloric effect and Critical Constants of Mott Insulator MnV2O4

X-ray absorption near edge spectra (XANES) and magnetization of Zn doped MnV2O4 have been measured and from the magnetic measurement the critical exponents and magnetocaloric effect have been estimated. The XANES study indicates that Zn doping does not change the valence states in Mn and V. It has been shown that the obtained values of critical exponents \b{eta}, γ and δ do not belong to universal class and the values are in between the 3D Heisenberg model and the mean field interaction model. The magnetization data follow the scaling equation and collapse into two branches indicating that the calculated critical exponents and critical temperature are unambiguous and intrinsic to the system. All the samples show large magneto-caloric effect. The second peak in magneto-caloric curve of Mn0.95Zn0.05V2O4 is due to the strong coupling between orbital and spin degrees of freedom. But 10% Zn doping reduces the residual spins on the V-V pairs resulting the decrease of coupling between orbital and spin degrees of freedom.

cond-mat.str-el↗

arXiv2013

Magnetic and Structural properties of $MnV_{2}O_{4}$

Magnetization, neutron diffraction and X-ray diffraction of Zn doped MnV2O4 as a function of temperature have been measured and the critical exponents and magnetocaloric effect of this system have been estimated. It is observed, that with increase in Zn substitution the noncollinear orientation of Mn spins with the V spins decreases which effectively leads to the decrease of structural transition temperature more rapidly than Curie temperature. It has been shown that the obtained values of β, γ and δ from different methods match very well. These values do not belong to universal class and the values are in between the 3D Heisenberg model and mean field interaction model. The magnetization data follow the scaling equation and collapse into two branches indicating that the calculated critical exponents and critical temperature are unambiguous and intrinsic to the system. The observed double peaks in magneto-caloric curve of Mn0.95Zn0.05V2O4 is due to the strong distortion of VO6 octahedra.

cond-mat.str-el↗