Search Results for author: Balaji Srinivasan

Found 8 papers, 3 papers with code

Abstracting Deep Neural Networks into Concept Graphs for Concept Level Interpretability

1 code implementation14 Aug 2020 Avinash Kori, Parth Natekar, Ganapathy Krishnamurthi, Balaji Srinivasan

Extracting such a graphical representation of the model's behavior on an abstract, higher conceptual level would unravel the learnings of these models and would help us to evaluate the steps taken by the model for predictions.

Brain Tumor Segmentation Decision Making +2

A Generalized Deep Learning Framework for Whole-Slide Image Segmentation and Analysis

2 code implementations1 Jan 2020 Mahendra Khened, Avinash Kori, Haran Rajkumar, Balaji Srinivasan, Ganapathy Krishnamurthi

However, the size of images and variability in histopathology tasks makes it a challenge to develop an integrated framework for histopathology image analysis.

Image Segmentation Lesion Detection +2

Modelling pressure-Hessian from local velocity gradients information in an incompressible turbulent flow field using deep neural networks

no code implementations19 Nov 2019 Nishant Parashar, Sawan S. Sinha, Balaji Srinivasan

The predictions made by the TBNN are tested against two different isotropic turbulence datasets at Reynolds number of 433 (JHTD) and 315 (UP Madrid turbulence database, UPMTD) and channel flow dataset at Reynolds number of 1000 (UT Texas and JHTD).

Distributed physics informed neural network for data-efficient solution to partial differential equations

no code implementations21 Jul 2019 Vikas Dwivedi, Nishant Parashar, Balaji Srinivasan

The physics informed neural network (PINN) is evolving as a viable method to solve partial differential equations.


Physics Informed Extreme Learning Machine (PIELM) -- A rapid method for the numerical solution of partial differential equations

1 code implementation8 Jul 2019 Vikas Dwivedi, Balaji Srinivasan

There has been rapid progress recently on the application of deep networks to the solution of partial differential equations, collectively labelled as Physics Informed Neural Networks (PINNs).

Enhanced Image Classification With Data Augmentation Using Position Coordinates

no code implementations5 Jan 2018 Avinash Kori, Ganapathy Krishnamurthi, Balaji Srinivasan

In this paper we propose the use of image pixel position coordinate system to improve image classification accuracy in various applications.

Classification Data Augmentation +2

Cannot find the paper you are looking for? You can Submit a new open access paper.