research
∙
05/15/2023
Straightening Out the Straight-Through Estimator: Overcoming Optimization Challenges in Vector Quantized Networks
This work examines the challenges of training neural networks using vect...
share
research
∙
12/22/2021
Meta-Learning and Self-Supervised Pretraining for Real World Image Translation
Recent advances in deep learning, in particular enabled by hardware adva...
research
∙
07/15/2021
Recurrent Parameter Generators
We present a generic method for recurrently using the same parameters fo...
research
∙
03/18/2021
The Low-Rank Simplicity Bias in Deep Networks
Modern deep neural networks are highly over-parameterized compared to th...
research
∙
08/15/2020
Cautious Adaptation For Reinforcement Learning in Safety-Critical Settings
Reinforcement learning (RL) in real-world safety-critical target setting...
research
∙
10/09/2019
Word Embedding Visualization Via Dictionary Learning
Co-occurrence statistics based word embedding techniques have proved to ...
research
∙
02/14/2019
Superposition of many models into one
We present a method for storing multiple models within a single set of p...
research
∙
03/31/2018
Learning Unsupervised Learning Rules
A major goal of unsupervised learning is to discover data representation...
research
∙
03/23/2018
Generalization Challenges for Neural Architectures in Audio Source Separation
Recent work has shown that recurrent neural networks can be trained to s...
research
∙
03/23/2018
Convolutional vs. Recurrent Neural Networks for Audio Source Separation
Recent work has shown that recurrent neural networks can be trained to s...
research
∙
02/22/2018
Adversarial Examples that Fool both Human and Computer Vision
Machine learning models are vulnerable to adversarial examples: small ch...
research
∙
11/28/2016
Emergence of foveal image sampling from learning to attend in visual scenes
We describe a neural attention model with a learnable retinal sampling l...
research
∙
12/20/2014
Discovering Hidden Factors of Variation in Deep Networks
Deep learning has enjoyed a great deal of success because of its ability...
research
∙
07/31/2013