
CrossTrajectory Representation Learning for ZeroShot Generalization in RL
A highly desirable property of a reinforcement learning (RL) agent – and...
read it

Understanding by Understanding Not: Modeling Negation in Language Models
Negation is a core construction in natural language. Despite being very ...
read it

ZeroShot Learning from scratch (ZFS): leveraging local compositional representations
Zeroshot classification is a generalization task where no instance from...
read it

Implicit Regularization in Deep Learning: A View from Function Space
We approach the problem of implicit regularization in deep learning from...
read it

Representation Learning with Video Deep InfoMax
Selfsupervised learning has made unsupervised pretraining relevant agai...
read it

DataEfficient Reinforcement Learning with Momentum Predictive Representations
While deep reinforcement learning excels at solving tasks where large am...
read it

Deep Reinforcement and InfoMax Learning
Our work is based on the hypothesis that a modelfree agent whose repres...
read it

ObjectCentric Image Generation from Layouts
Despite recent impressive results on singleobject and singledomain ima...
read it

An endtoend approach for the verification problem: learning the right distance
In this contribution, we augment the metric learning setting by introduc...
read it

AttractionRepulsion ActorCritic for Continuous Control Reinforcement Learning
Continuous control tasks in reinforcement learning are important because...
read it

Unsupervised State Representation Learning in Atari
State representation learning, or the ability to capture latent generati...
read it

Learning Representations by Maximizing Mutual Information Across Views
We propose an approach to selfsupervised representation learning based ...
read it

Batch weight for domain adaptation with mass shift
Unsupervised domain transfer is the task of transferring or translating ...
read it

Leveraging exploration in offpolicy algorithms via normalizing flows
Exploration is a crucial component for discovering approximately optimal...
read it

Prediction of Progression to Alzheimer`s disease with Deep InfoMax
Arguably, unsupervised learning plays a crucial role in the majority of ...
read it

SpatioTemporal Deep Graph Infomax
Spatiotemporal graphs such as traffic networks or gene regulatory syste...
read it

Adversarial Mixup Resynthesizers
In this paper, we explore new approaches to combining information encode...
read it

Deep Graph Infomax
We present Deep Graph Infomax (DGI), a general approach for learning nod...
read it

Learning deep representations by mutual information estimation and maximization
Many popular representationlearning algorithms use training objectives ...
read it

Online Adaptative Curriculum Learning for GANs
Generative Adversarial Networks (GANs) can successfully learn a probabil...
read it

MINE: Mutual Information Neural Estimation
We argue that the estimation of the mutual information between high dime...
read it

ACtuAL: ActorCritic Under Adversarial Learning
Generative Adversarial Networks (GANs) are a powerful framework for deep...
read it

Variance Regularizing Adversarial Learning
We introduce a novel approach for training adversarial models by replaci...
read it

BoundarySeeking Generative Adversarial Networks
We introduce a novel approach to training generative adversarial network...
read it

MaximumLikelihood Augmented Discrete Generative Adversarial Networks
Despite the successes in capturing continuous distributions, the applica...
read it

Recurrent Neural Networks for Spatiotemporal Dynamics of Intrinsic Networks from fMRI Data
Functional magnetic resonance imaging (fMRI) of temporallycoherent bloo...
read it

Variational Autoencoders for Feature Detection of Magnetic Resonance Imaging Data
Independent component analysis (ICA), as an approach to the blind source...
read it

Iterative Refinement of Approximate Posterior for Training Directed Belief Networks
Variational methods that rely on a recognition network to approximate th...
read it
R Devon Hjelm
is this you? claim profile