334 citations · 726 across the 11 of their papers we have counts for
7 papers · 1 filter
Diverse Ensembles Improve Calibration
Asa Cooper Stickland, Iain Murray
Modern deep neural networks can produce badly calibrated predictions, especially when train and test distributions are mismatched. Training an ensemble of models and averaging thei…
CloudLSTM: A Recurrent Neural Model for Spatiotemporal Point-cloud Stream Forecasting
Chaoyun Zhang, Marco Fiore, Iain Murray +1
This paper introduces CloudLSTM, a new branch of recurrent neural models tailored to forecasting over data streams generated by geospatial point-cloud sources. We design a Dynamic…
Dynamic Evaluation of Transformer Language Models
Ben Krause, Emmanuel Kahembwe, Iain Murray +1
This research note combines two methods that have recently improved the state of the art in language modeling: Transformers and dynamic evaluation. Transformers use stacked layers…
Mode Normalization
Lucas Deecke, Iain Murray, Hakan Bilen
Normalization methods are a central building block in the deep learning toolbox. They accelerate and stabilize training, while decreasing the dependence on manually tuned learning…
Neural Autoregressive Distribution Estimation
Benigno Uria, Marc-Alexandre Côté, Karol Gregor +2
We present Neural Autoregressive Distribution Estimation (NADE) models, which are neural network architectures applied to the problem of unsupervised distribution and density estim…
MADE: Masked Autoencoder for Distribution Estimation
Mathieu Germain, Karol Gregor, Iain Murray +1
There has been a lot of recent interest in designing neural network models to estimate a distribution from a set of examples. We introduce a simple modification for autoencoder neu…