no code implementations • 12 Jan 2019 • Aaron Vose, Jacob Balma, Alex Heye, Alessandro Rigazzi, Charles Siegel, Diana Moise, Benjamin Robbins, Rangan Sukumar
We propose a genetic algorithm (GA) for hyperparameter optimization of artificial neural networks which includes chromosomal crossover as well as a decoupling of parameters (i. e., weights and biases) from hyperparameters (e. g., learning rate, weight decay, and dropout) during sexual reproduction.
no code implementations • 13 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.
1 code implementation • 2 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.
no code implementations • 15 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.
1 code implementation • 7 Dec 2017 • Garrett B. Goh, Charles Siegel, Abhinav Vishnu, Nathan O. Hodas
With access to large datasets, deep neural networks (DNN) have achieved human-level accuracy in image and speech recognition tasks.
4 code implementations • 6 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.
2 code implementations • 5 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.
2 code implementations • 20 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.
no code implementations • 3 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.
no code implementations • 7 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