Search Results for author: Shreyas Malakarjun Patil

Found 6 papers, 1 papers with code

PHEW: Paths with Higher Edge-Weights give ''winning tickets'' without training data

no code implementations1 Jan 2021 Shreyas Malakarjun Patil, Constantine Dovrolis

Then, we show that Paths with Higher Edge-Weights (PHEW) at initialization have higher loss gradient magnitude, resulting in more efficient training.

PHEW: Constructing Sparse Networks that Learn Fast and Generalize Well without Training Data

1 code implementation22 Oct 2020 Shreyas Malakarjun Patil, Constantine Dovrolis

Our work is based on a recently proposed decomposition of the Neural Tangent Kernel (NTK) that has decoupled the dynamics of the training process into a data-dependent component and an architecture-dependent kernel - the latter referred to as Path Kernel.

Siamese LSTM based Fiber Structural Similarity Network (FS2Net) for Rotation Invariant Brain Tractography Segmentation

no code implementations28 Dec 2017 Shreyas Malakarjun Patil, Aditya Nigam, Arnav Bhavsar, Chiranjoy Chattopadhyay

In this paper, we propose a novel deep learning architecture combining stacked Bi-directional LSTM and LSTMs with the Siamese network architecture for segmentation of brain fibers, obtained from tractography data, into anatomically meaningful clusters.

Segmentation

BrainSegNet : A Segmentation Network for Human Brain Fiber Tractography Data into Anatomically Meaningful Clusters

no code implementations14 Oct 2017 Tushar Gupta, Shreyas Malakarjun Patil, Mukkaram Tailor, Daksh Thapar, Aditya Nigam

The segregation of brain fiber tractography data into distinct and anatomically meaningful clusters can help to comprehend the complex brain structure and early investigation and management of various neural disorders.

Classification General Classification +1

UBSegNet: Unified Biometric Region of Interest Segmentation Network

no code implementations26 Sep 2017 Ranjeet Ranjan Jha, Daksh Thapar, Shreyas Malakarjun Patil, Aditya Nigam

In this paper, we have proposed a novel end-to-end, Unified Biometric ROI Segmentation Network (UBSegNet), for extracting region of interest from five different biometric traits viz.

General Classification Management +1

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