Statistical Learning
Predicting Organic Reaction Outcomes with Weisfeiler-Lehman Network
Wengong Jin, Connor Coley, Regina Barzilay, Tommi Jaakkola
Neural Information Processing Systems http://nips.cc/
Online to Offline Conversions, Universality and Adaptive Minibatch Sizes
Over the past years data adaptiveness has proven to be crucial to the success of learning algorithms. The objective function underlying "big data" applications often demonstrates intricate structure: the scale and smoothness are often unknown and may change substantially in between different regions/directions, [
PRUNE: Preserving Proximity and Global Ranking for Network Embedding
Yi-An Lai, Chin-Chi Hsu, Wen Hao Chen, Mi-Yen Yeh, Shou-De Lin
We investigate an unsupervised generative approach for network embedding.
Unified representation of tractography and diffusion-weighted MRI data using sparse multidimensional arrays
Cesar F. Caiafa, Olaf Sporns, Andrew Saykin, Franco Pestilli
Diffusion-weighted MRI allows us to estimate structural brain connections in-vivo by measuring the diffusion of water molecules at different spatial directions.
Prototypical Networks for Few-shot Learning
Jake Snell, Kevin Swersky, Richard Zemel
Prototypical Networks learn a metric space in which classification can be performed by computing distances to prototype representations of each class.
Random Projection Filter Bank for Time Series Data
Amir-massoud Farahmand, Sepideh Pourazarm, Daniel Nikovski
We propose Random Projection Filter Bank (RPFB) as a generic and simple approach to extract features from time series data.
Fitting Low-Rank Tensors in Constant Time
Neural Information Processing Systems http://nips.cc/
Adversarial Surrogate Losses for Ordinal Regression
Rizal Fathony, Mohammad Ali Bashiri, Brian Ziebart
Neural Information Processing Systems http://nips.cc/
Extracting low-dimensional dynamics from multiple large-scale neural population recordings by learning to predict correlations
Marcel Nonnenmacher, Srinivas C. Turaga, Jakob H. Macke
Our algorithm scales to data comprising millions of observed dimensions, making it possible to access dynamics distributed across large populations or multiple brain areas.