
MemoryBased Graph Networks
Graph neural networks (GNNs) are a class of deep models that operate on ...
read it

Learning Global and Local Consistent Representations for Unsupervised Image Retrieval via Deep Graph Diffusion Networks
Diffusion has shown great success in improving accuracy of unsupervised ...
read it

SplitSR: An EndtoEnd Approach to SuperResolution on Mobile Devices
Superresolution (SR) is a coveted image processing technique for mobile...
read it

Neural Networks with Cheap Differential Operators
Gradients of neural networks can be computed efficiently for any archite...
read it

Fast Convergence of Natural Gradient Descent for Overparameterized Neural Networks
Natural gradient descent has proven effective at mitigating the effects ...
read it

Functional Variational Bayesian Neural Networks
Variational Bayesian neural networks (BNNs) perform variational inferenc...
read it

Neural Data Server: A LargeScale Search Engine for Transfer Learning Data
Transfer learning has proven to be a successful technique to train deep ...
read it

Benchmarking ModelBased Reinforcement Learning
Modelbased reinforcement learning (MBRL) is widely seen as having the p...
read it

SelfTuning Networks: Bilevel Optimization of Hyperparameters using Structured BestResponse Functions
Hyperparameter optimization can be formulated as a bilevel optimization ...
read it

Multinode Bertpretraining: Costefficient Approach
Recently, large scale Transformerbased language models such as BERT, GP...
read it

MANGA: Method Agnostic Neuralpolicy Generalization and Adaptation
In this paper we target the problem of transferring policies across mult...
read it

An Empirical Study of Representation Learning for Reinforcement Learning in Healthcare
Reinforcement Learning (RL) has recently been applied to sequential esti...
read it

FewShot SingleView 3D Object Reconstruction with Compositional Priors
The impressive performance of deep convolutional neural networks in sing...
read it

A Study of Gradient Variance in Deep Learning
The impact of gradient noise on training deep models is widely acknowled...
read it

Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One
We propose to reinterpret a standard discriminative classifier of p(yx)...
read it

High Mutual Information in Representation Learning with Symmetric Variational Inference
We introduce the Mutual Information Machine (MIM), a novel formulation o...
read it

Invertible Residual Networks
Reversible deep networks provide useful theoretical guarantees and have ...
read it

Reproducibility in Machine Learning for Health
Machine learning algorithms designed to characterize, monitor, and inter...
read it

Efficient Graph Generation with Graph Recurrent Attention Networks
We propose a new family of efficient and expressive deep generative mode...
read it

Alchemy: A Quantum Chemistry Dataset for Benchmarking AI Models
We introduce a new molecular dataset, named Alchemy, for developing mach...
read it

Towards the Role of Theory of Mind in Explanation
Theory of Mind is commonly defined as the ability to attribute mental st...
read it

Using Generative Models for Pediatric wbMRI
Early detection of cancer is key to a good prognosis and requires freque...
read it

Hierarchical Recurrent Attention Networks for Structured Online Maps
In this paper, we tackle the problem of online road network extraction f...
read it

Concurrent Meta Reinforcement Learning
Stateoftheart meta reinforcement learning algorithms typically assume...
read it

GatedSCNN: Gated Shape CNNs for Semantic Segmentation
Current stateoftheart methods for image segmentation form a dense ima...
read it

Learning to Predict 3D Objects with an Interpolationbased Differentiable Renderer
Many machine learning models operate on images, but ignore the fact that...
read it

A DerivativeFree Method for Solving Elliptic Partial Differential Equations with Deep Neural Networks
We introduce a deep neural network based method for solving a class of e...
read it

BatchEnsemble: an Alternative Approach to Efficient Ensemble and Lifelong Learning
Ensembles, where multiple neural networks are trained individually and t...
read it

DeepSpline: DataDriven Reconstruction of Parametric Curves and Surfaces
Reconstruction of geometry based on different input modes, such as image...
read it

MetaSim: Learning to Generate Synthetic Datasets
Training models to highend performance requires availability of large l...
read it

Experience Replay with Likelihoodfree Importance Weights
The use of past experiences to accelerate temporal difference (TD) learn...
read it

Neural Ordinary Differential Equations
We introduce a new family of deep neural network models. Instead of spec...
read it

WCellNet: Multiframe Interpolation of Cellular Microscopy Videos
Deep Neural Networks are increasingly used in video frame interpolation ...
read it

CostEfficient Online Hyperparameter Optimization
Recent work on hyperparameters optimization (HPO) has shown the possibil...
read it

Deep MultiSensor Lane Detection
Reliable and accurate lane detection has been a longstanding problem in...
read it

Aligning Superhuman AI and Human Behavior: Chess as a Model System
As artificial intelligence becomes increasingly intelligent—in some case...
read it

SurfConv: Bridging 3D and 2D Convolution for RGBD Images
We tackle the problem of using 3D information in convolutional neural ne...
read it

Sorting out Lipschitz function approximation
Training neural networks subject to a Lipschitz constraint is useful for...
read it

Music Artist Classification with Convolutional Recurrent Neural Networks
Previous attempts at music artist classification use framelevel audio f...
read it

DMMNet: Differentiable MaskMatching Network for Video Object Segmentation
In this paper, we propose the differentiable maskmatching network (DMM...
read it

Dense RepPoints: Representing Visual Objects with Dense Point Sets
We present an object representation, called Dense RepPoints, for flexibl...
read it

SUMO: Unbiased Estimation of Log Marginal Probability for Latent Variable Models
Standard variational lower bounds used to train latent variable models p...
read it

RigNet: Neural Rigging for Articulated Characters
We present RigNet, an endtoend automated method for producing animatio...
read it

Finegrained Video Classification and Captioning
We describe a DNN for finegrained action classification and video capti...
read it

Scalable Recommender Systems through Recursive Evidence Chains
Recommender systems can be formulated as a matrix completion problem, pr...
read it

A CoordinateFree Construction of Scalable Natural Gradient
Most neural networks are trained using firstorder optimization methods,...
read it

Reversible Recurrent Neural Networks
Recurrent neural networks (RNNs) provide stateoftheart performance in...
read it

Speaker diarization with sessionlevel speaker embedding refinement using graph neural networks
Deep speaker embedding models have been commonly used as a building bloc...
read it

Eigenvalue Corrected Noisy Natural Gradient
Variational Bayesian neural networks combine the flexibility of deep lea...
read it

Lookahead Optimizer: k steps forward, 1 step back
The vast majority of successful deep neural networks are trained using v...
read it
UNIVERSITY OF TORONTO
The University of Toronto is a public research university in Toronto, Ontario, Canada, located on the grounds that surround Queen's Park.