Search Results for author: Abhinav Vishnu

Found 15 papers, 5 papers with code

CFDNet: a deep learning-based accelerator for fluid simulations

no code implementations9 May 2020 Octavi Obiols-Sales, Abhinav Vishnu, Nicholas Malaya, Aparna Chandramowlishwaran

CFD is widely used in physical system design and optimization, where it is used to predict engineering quantities of interest, such as the lift on a plane wing or the drag on a motor vehicle.

Multimodal Deep Neural Networks using Both Engineered and Learned Representations for Biodegradability Prediction

no code implementations13 Aug 2018 Garrett B. Goh, Khushmeen Sakloth, Charles Siegel, Abhinav Vishnu, Jim Pfaendtner

Deep learning algorithms excel at extracting patterns from raw data, and with large datasets, they have been very successful in computer vision and natural language applications.

Feature Engineering Representation Learning

ColdRoute: Effective Routing of Cold Questions in Stack Exchange Sites

1 code implementation2 Jul 2018 Jiankai Sun, Abhinav Vishnu, Aniket Chakrabarti, Charles Siegel, Srinivasan Parthasarathy

Using data from eight stack exchange sites, we are able to improve upon the routing metrics (Precision$@1$, Accuracy, MRR) over the state-of-the-art models such as semantic matching by $159. 5\%$,$31. 84\%$, and $40. 36\%$ for cold questions posted by existing askers, and $123. 1\%$, $27. 03\%$, and $34. 81\%$ for cold questions posted by new askers respectively.

GossipGraD: Scalable Deep Learning using Gossip Communication based Asynchronous Gradient Descent

no code implementations15 Mar 2018 Jeff Daily, Abhinav Vishnu, Charles Siegel, Thomas Warfel, Vinay Amatya

In this paper, we present GossipGraD - a gossip communication protocol based Stochastic Gradient Descent (SGD) algorithm for scaling Deep Learning (DL) algorithms on large-scale systems.

SMILES2Vec: An Interpretable General-Purpose Deep Neural Network for Predicting Chemical Properties

4 code implementations6 Dec 2017 Garrett B. Goh, Nathan O. Hodas, Charles Siegel, Abhinav Vishnu

Chemical databases store information in text representations, and the SMILES format is a universal standard used in many cheminformatics software.

Feature Engineering

How Much Chemistry Does a Deep Neural Network Need to Know to Make Accurate Predictions?

2 code implementations5 Oct 2017 Garrett B. Goh, Charles Siegel, Abhinav Vishnu, Nathan O. Hodas, Nathan Baker

The meteoric rise of deep learning models in computer vision research, having achieved human-level accuracy in image recognition tasks is firm evidence of the impact of representation learning of deep neural networks.

Representation Learning

Chemception: A Deep Neural Network with Minimal Chemistry Knowledge Matches the Performance of Expert-developed QSAR/QSPR Models

2 code implementations20 Jun 2017 Garrett B. Goh, Charles Siegel, Abhinav Vishnu, Nathan O. Hodas, Nathan Baker

We then show how Chemception can serve as a general-purpose neural network architecture for predicting toxicity, activity, and solvation properties when trained on a modest database of 600 to 40, 000 compounds.

Feature Engineering Image Classification +1

Deep Learning for Computational Chemistry

no code implementations17 Jan 2017 Garrett B. Goh, Nathan O. Hodas, Abhinav Vishnu

The rise and fall of artificial neural networks is well documented in the scientific literature of both computer science and computational chemistry.

Protein Structure Prediction Speech Recognition

Adaptive Neuron Apoptosis for Accelerating Deep Learning on Large Scale Systems

no code implementations3 Oct 2016 Charles Siegel, Jeff Daily, Abhinav Vishnu

We present novel techniques to accelerate the convergence of Deep Learning algorithms by conducting low overhead removal of redundant neurons -- apoptosis of neurons -- which do not contribute to model learning, during the training phase itself.

General Classification

A Data-Driven Approach for Semantic Role Labeling from Induced Grammar Structures in Language

no code implementations20 Jun 2016 Vivek Datla, David Lin, Max Louwerse, Abhinav Vishnu

Specifically we develop a modified-ADIOS algorithm based on ADIOS Solan et al. (2005) to learn grammar structures, and use these grammar structures to learn the rules for identifying the semantic roles based on the context in which the grammar structures appeared.

Semantic Role Labeling

Distributed TensorFlow with MPI

no code implementations7 Mar 2016 Abhinav Vishnu, Charles Siegel, Jeffrey Daily

Machine Learning and Data Mining (MLDM) algorithms are becoming increasingly important in analyzing large volume of data generated by simulations, experiments and mobile devices.

Distributed, Parallel, and Cluster Computing

Fast Support Vector Machines Using Parallel Adaptive Shrinking on Distributed Systems

no code implementations19 Jun 2014 Jeyanthi Narasimhan, Abhinav Vishnu, Lawrence Holder, Adolfy Hoisie

Under sample elimination, several heuristics for {\em earliest possible} to {\em lazy} elimination of non-contributing samples are proposed.

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