research
∙
05/16/2022
The Primacy Bias in Deep Reinforcement Learning
This work identifies a common flaw of deep reinforcement learning (RL) a...
share
research
∙
02/03/2022
Generative Flow Networks for Discrete Probabilistic Modeling
We present energy-based generative flow networks (EB-GFN), a novel proba...
research
∙
12/17/2021
MIDI-DDSP: Detailed Control of Musical Performance via Hierarchical Modeling
Musical expression requires control of both what notes are played, and h...
research
∙
11/18/2020
Gradient Starvation: A Learning Proclivity in Neural Networks
We identify and formalize a fundamental gradient descent phenomenon resu...
research
∙
03/28/2020
Countering Language Drift with Seeded Iterated Learning
Supervised learning methods excel at capturing statistical properties of...
research
∙
03/02/2020
Out-of-Distribution Generalization via Risk Extrapolation (REx)
Generalizing outside of the training distribution is an open challenge f...
research
∙
02/17/2020
Augmented Normalizing Flows: Bridging the Gap Between Generative Flows and Latent Variable Models
In this work, we propose a new family of generative flows on an augmente...
research
∙
03/18/2019
Counterpoint by Convolution
Machine learning models of music typically break up the task of composit...
research
∙
01/24/2019
Maximum Entropy Generators for Energy-Based Models
Unsupervised learning is about capturing dependencies between variables ...
research
∙
11/29/2017
HoME: a Household Multimodal Environment
We introduce HoME: a Household Multimodal Environment for artificial age...
research
∙
10/13/2017
Bayesian Hypernetworks
We propose Bayesian hypernetworks: a framework for approximate Bayesian ...
research
∙
09/22/2017
FiLM: Visual Reasoning with a General Conditioning Layer
We introduce a general-purpose conditioning method for neural networks c...
research
∙
07/02/2017
Modulating early visual processing by language
It is commonly assumed that language refers to high-level visual concept...
research
∙
03/31/2017
Improved Training of Wasserstein GANs
Generative Adversarial Networks (GANs) are powerful generative models, b...
research
∙
12/12/2016
Generalizable Features From Unsupervised Learning
Humans learn a predictive model of the world and use this model to reaso...
research
∙
05/12/2016
Movie Description
Audio Description (AD) provides linguistic descriptions of movies and al...
research
∙
05/03/2015
ReNet: A Recurrent Neural Network Based Alternative to Convolutional Networks
In this paper, we propose a deep neural network architecture for object ...
research
∙
02/10/2015
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
Inspired by recent work in machine translation and object detection, we ...
research
∙
12/21/2013
An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks
Catastrophic forgetting is a problem faced by many machine learning mode...
research
∙
02/18/2013
Maxout Networks
We consider the problem of designing models to leverage a recently intro...
research
∙
06/24/2012
