Self-Supervised Learning (SSL) methods operate on unlabeled data to lear...
Several self-supervised representation learning methods have been propos...
Modern decision-making systems, from robots to web recommendation engine...
Models that can actively seek out the best quality training data hold th...
Goal-conditioned reinforcement learning (RL) is a promising direction fo...
Learning to control an agent from data collected offline in a rich
pixel...
We propose a novel regularizer for supervised learning called Conditioni...
A person walking along a city street who tries to model all aspects of t...
Recurrent neural networks have a strong inductive bias towards learning
...
Vector Quantization (VQ) is a method for discretizing latent representat...
Deep learning has advanced from fully connected architectures to structu...
Japan is a unique country with a distinct cultural heritage, which is
re...
Deep learning has seen a movement away from representing examples with a...
An important development in deep learning from the earliest MLPs has bee...
We introduce and motivate generative modeling as a central task for mach...
Robust perception relies on both bottom-up and top-down signals. Bottom-...
Modeling a structured, dynamic environment like a video game requires ke...
The latent variables learned by VAEs have seen considerable interest as ...
From classifying handwritten digits to generating strings of text, the
d...
Deep networks have achieved excellent results in perceptual tasks, yet t...
Kuzushiji, a cursive writing style, had been used in Japan for over a
th...
We present GraphMix, a regularization technique for Graph Neural Network...
Learning modular structures which reflect the dynamics of the environmen...
Adversarial robustness has become a central goal in deep learning, both ...
Machine learning promises methods that generalize well from finite label...
We introduce Interpolation Consistency Training (ICT), a simple and
comp...
In this paper, we explore new approaches to combining information encode...
Much of machine learning research focuses on producing models which perf...
Deep networks often perform well on the data manifold on which they are
...
Deep networks have achieved impressive results across a variety of impor...
Directed latent variable models that formulate the joint distribution as...
Generative Adversarial Networks (GANs) are a powerful framework for deep...
The Teacher Forcing algorithm trains recurrent networks by supplying obs...
We introduce the adversarially learned inference (ALI) model, which join...
Theano is a Python library that allows to define, optimize, and evaluate...
We explore the question of whether the representations learned by classi...
Humans are able to accelerate their learning by selecting training mater...