Search Results for author: Peyton Greenside

Found 5 papers, 4 papers with code

A Hierarchical Approach to Scaling Batch Active Search Over Structured Data

1 code implementation20 Jul 2020 Vivek Myers, Peyton Greenside

As modern data sets grow, so does the need to scale active search to large data sets and batch sizes.

Bayesian Optimization

Learning Important Features Through Propagating Activation Differences

11 code implementations ICML 2017 Avanti Shrikumar, Peyton Greenside, Anshul Kundaje

Here we present DeepLIFT (Deep Learning Important FeaTures), a method for decomposing the output prediction of a neural network on a specific input by backpropagating the contributions of all neurons in the network to every feature of the input.

Interpretable Machine Learning

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