ProtoryNet - Interpretable Text Classification Via Prototype Trajectories

1 code implementation • 3 Jul 2020 • Dat Hong, Tong Wang, Stephen S. Baek

We propose a novel interpretable deep neural network for text classification, called ProtoryNet, based on a new concept of prototype trajectories.

General Classification Sentence +2

Deep learning for synthetic microstructure generation in a materials-by-design framework for heterogeneous energetic materials

no code implementations • 5 Apr 2020 • Sehyun Chun, Sidhartha Roy, Yen Thi Nguyen, Joseph B. Choi, H. S. Udaykumar, Stephen S. Baek

Emerging multi-scale predictive models of HE response to loads account for the physics at the meso-scale, i. e. at the scale of statistically representative clusters of particles and other features in the microstructure.

NADS-Net: A Nimble Architecture for Driver and Seat Belt Detection via Convolutional Neural Networks

no code implementations • 8 Oct 2019 • Sehyun Chun, Nima Hamidi Ghalehjegh, Joseph B. Choi, Chris W. Schwarz, John G. Gaspar, Daniel V. McGehee, Stephen S. Baek

A new convolutional neural network (CNN) architecture for 2D driver/passenger pose estimation and seat belt detection is proposed in this paper.

Autonomous Driving Pose Estimation