Calibration is a fundamental property of a good predictive model: it req...
The practical success of overparameterized neural networks has motivated...
Real-world text classification tasks often require many labeled training...
We introduce Multi-Frame Cross-Entropy training (MFCE) for convolutional...
Many conversational agents in the market today follow a standard bot
dev...
In this paper, we propose a novel Convolutional Neural Network (CNN)
arc...
We examine Deep Canonically Correlated LSTMs as a way to learn nonlinear...