I'm
Anshul Shivhare
Senior AI Engineer at EY-GDS, Mtech Student@ IISc Bangalore, Artificial Intelligence
I'm
Hi! I am Anshul, a Data Scientist at EY-GDS india. Completed my MTech in Artificial Intelligence from Indian Institute of Science (IISc) Bangalore, My research work at IISc was focused on computer vision in Spectrum Lab under the guidance of Prof. Chandra Sekhar Seelamantula.
My research work included medical image classification and visualization (Explainability).
I completed my B.E in Computer Science Engineering from RGPV Bhopal. I actively work in the fields of data science, classical machine learning and deep learning.
Current Ongoing work : End to End deployment of Spend Classification Engine on Azure databricks.
My Resume
Research
Classification and Visualization of Medical Images
OCT (Optical Coherence Tomography) Data:
Convivo Brain Imaging:
Noise Removal Techniques:
Evaluation Metrics:
Visualization Techniques:
Performance Metrics and Use Case:
Need for unconstrained methods in solving constrained problems. Necessary conditions of unconstrained optimization, Structure of methods, quadratic models. Methods of line search, Armijo-Goldstein and Wolfe conditions for partial line search. Global convergence theorem, Steepest descent method. Quasi-Newton methods: DFP, BFGS, Broyden family. Conjugate-direction methods: Fletcher-Reeves, Polak-Ribierre. Derivative-free methods: finite differencing. Restricted step methods. Methods for sums of squares and nonlinear equations. Linear and Quadratic Programming. Duality in optimization.
Probability spaces, conditional probability, independence, random variables, distribution functions, multiple random variables and joint distributions, moments, characteristic functions and moment generating functions, conditional expectation, sequence of random variables and convergence concepts, law of large numbers, central limit theorem, stochastic processes, Markov chains, Poisson process.
Bi-LSTM, VAE, GANs, Explainability in Deep Nets, Grad CAMs, Score CAMs, Adverserial Attcks on Deep Nets, Knowledge Distillation, Lipchitz Constants for Deep Nets.
Introduction to pattern recognition, Bayesian decision theory, supervised learning from data, parametric and non parametric estimation of density functions, Bayes and nearest neighbor classifiers, introduction to statistical learning theory, empirical risk minimization, discriminant functions, learning linear discriminant functions, Perceptron, linear least squares regression, LMS algorithm, artificial neural networks for pattern classification and function learning, multilayer feed forward networks, backpropagation, RBF networks, deep neural Networks, support vector machines, kernel based methods, feature selection and dimensionality reduction methods