Structured kernel interpolation (SKI) accelerates Gaussian process (GP) inference by interpolating the kernel covariance function using a dense grid of inducing points, whose corresponding kernel matrix is highly structured and thus amenable to fast linear algebra.
Structured kernel interpolation (SKI) is among the most scalable methods: by placing inducing points on a dense grid and using structured matrix algebra, SKI achieves per-iteration time of O(n + m log m) for approximate inference.
We introduce the deep inside-outside recursive autoencoder (DIORA), a fully-unsupervised method for discovering syntax that simultaneously learns representations for constituents within the induced tree.
We introduce deep inside-outside recursive autoencoders (DIORA), a fully-unsupervised method for discovering syntax that simultaneously learns representations for constituents within the induced tree.
We present a novel technique for segmenting chat conversations using the information bottleneck method (Tishby et al., 2000), augmented with sequential continuity constraints.
Motivated by these practical issues, we propose a novel curriculum inspired training procedure for Memory Networks to improve the performance for machine comprehension with relatively small volumes of training data.
The available data is then augmented with data generated from the ODE, and the anomaly detector is retrained on this augmented dataset.