-
Whitening and second order optimization both destroy information about the dataset, and can make generalization impossible
Machine learning is predicated on the concept of generalization: a model...
08/17/2020 ∙ by Neha S. Wadia, et al. ∙
0
∙
share
read it
-
NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections
We present a learning-based method for synthesizing novel views of compl...
08/05/2020 ∙ by Ricardo Martin-Brualla, et al. ∙
0
∙
share
read it
-
Trading Off Diversity and Quality in Natural Language Generation
For open-ended language generation tasks such as storytelling and dialog...
04/22/2020 ∙ by Hugh Zhang, et al. ∙
0
∙
share
read it
-
Human and Automatic Detection of Generated Text
With the advent of generative models with a billion parameters or more, ...
11/02/2019 ∙ by Daphne Ippolito, et al. ∙
0
∙
share
read it
-
Neural Assistant: Joint Action Prediction, Response Generation, and Latent Knowledge Reasoning
Task-oriented dialog presents a difficult challenge encompassing multipl...
10/31/2019 ∙ by Arvind Neelakantan, et al. ∙
0
∙
share
read it
-
Taskmaster-1: Toward a Realistic and Diverse Dialog Dataset
A significant barrier to progress in data-driven approaches to building ...
09/01/2019 ∙ by Bill Byrne, et al. ∙
0
∙
share
read it
-
Parallel Scheduled Sampling
Auto-regressive models are widely used in sequence generation problems. ...
06/11/2019 ∙ by Daniel Duckworth, et al. ∙
0
∙
share
read it
-
The Importance of Generation Order in Language Modeling
Neural language models are a critical component of state-of-the-art syst...
08/23/2018 ∙ by Nicolas Ford, et al. ∙
0
∙
share
read it
-
Stochastic natural gradient descent draws posterior samples in function space
Natural gradient descent (NGD) minimises the cost function on a Riemanni...
06/25/2018 ∙ by Samuel L. Smith, et al. ∙
0
∙
share
read it
