UNIVERSITY OF TORONTO

research

∙ 02/21/2020

Memory-Based Graph Networks

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

Amir Hosein Khasahmadi, et al. ∙

research

∙ 01/20/2021

SplitSR: An End-to-End Approach to Super-Resolution on Mobile Devices

Super-resolution (SR) is a coveted image processing technique for mobile...

Xin Liu, et al. ∙

research

∙ 01/05/2020

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 ...

Zhiyong Dou, et al. ∙

research

∙ 12/08/2019

Neural Networks with Cheap Differential Operators

Gradients of neural networks can be computed efficiently for any archite...

Ricky T. Q. Chen, et al. ∙

research

∙ 05/27/2019

Fast Convergence of Natural Gradient Descent for Overparameterized Neural Networks

Natural gradient descent has proven effective at mitigating the effects ...

Guodong Zhang, et al. ∙

research

∙ 03/14/2019

Functional Variational Bayesian Neural Networks

Variational Bayesian neural networks (BNNs) perform variational inferenc...

Shengyang Sun, et al. ∙

research

∙ 01/09/2020

Neural Data Server: A Large-Scale Search Engine for Transfer Learning Data

Transfer learning has proven to be a successful technique to train deep ...

Xi Yan, et al. ∙

research

∙ 07/03/2019

Benchmarking Model-Based Reinforcement Learning

Model-based reinforcement learning (MBRL) is widely seen as having the p...

Tingwu Wang, et al. ∙

research

∙ 03/07/2019

Self-Tuning Networks: Bilevel Optimization of Hyperparameters using Structured Best-Response Functions

Hyperparameter optimization can be formulated as a bilevel optimization ...

Matthew MacKay, et al. ∙

research

∙ 08/01/2020

Multi-node Bert-pretraining: Cost-efficient Approach

Recently, large scale Transformer-based language models such as BERT, GP...

Jiahuang Lin, et al. ∙

research

∙ 11/19/2019

MANGA: Method Agnostic Neural-policy Generalization and Adaptation

In this paper we target the problem of transferring policies across mult...

Homanga Bharadhwaj, et al. ∙

research

∙ 11/23/2020

An Empirical Study of Representation Learning for Reinforcement Learning in Healthcare

Reinforcement Learning (RL) has recently been applied to sequential esti...

Taylor W. Killian, et al. ∙

research

∙ 06/07/2021

TENGraD: Time-Efficient Natural Gradient Descent with Exact Fisher-Block Inversion

This work proposes a time-efficient Natural Gradient Descent method, cal...

Saeed Soori, et al. ∙

research

∙ 04/14/2020

Few-Shot Single-View 3-D Object Reconstruction with Compositional Priors

The impressive performance of deep convolutional neural networks in sing...

Mateusz Michalkiewicz, et al. ∙

research

∙ 07/09/2020

A Study of Gradient Variance in Deep Learning

The impact of gradient noise on training deep models is widely acknowled...

Fartash Faghri, et al. ∙

research

∙ 12/06/2019

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(y|x)...

Will Grathwohl, et al. ∙

research

∙ 09/13/2021

Online Unsupervised Learning of Visual Representations and Categories

Real world learning scenarios involve a nonstationary distribution of cl...

Mengye Ren, et al. ∙

research

∙ 10/04/2019

High Mutual Information in Representation Learning with Symmetric Variational Inference

We introduce the Mutual Information Machine (MIM), a novel formulation o...

Micha Livne, et al. ∙

research

∙ 11/02/2018

Invertible Residual Networks

Reversible deep networks provide useful theoretical guarantees and have ...

Jens Behrmann, et al. ∙

research

∙ 07/02/2019

Reproducibility in Machine Learning for Health

Machine learning algorithms designed to characterize, monitor, and inter...

Matthew B. A. McDermott, et al. ∙

research

∙ 10/02/2019

Efficient Graph Generation with Graph Recurrent Attention Networks

We propose a new family of efficient and expressive deep generative mode...

Renjie Liao, et al. ∙

research

∙ 04/18/2022

Hierarchical Optimal Transport for Comparing Histopathology Datasets

Scarcity of labeled histopathology data limits the applicability of deep...

Anna Yeaton, et al. ∙

research

∙ 06/22/2019

Alchemy: A Quantum Chemistry Dataset for Benchmarking AI Models

We introduce a new molecular dataset, named Alchemy, for developing mach...

Guangyong Chen, et al. ∙

research

∙ 05/06/2020

Towards the Role of Theory of Mind in Explanation

Theory of Mind is commonly defined as the ability to attribute mental st...

Maayan Shvo, et al. ∙

research

∙ 06/01/2020

Using Generative Models for Pediatric wbMRI

Early detection of cancer is key to a good prognosis and requires freque...

Alex Chang, et al. ∙

research

∙ 12/22/2020

Hierarchical Recurrent Attention Networks for Structured Online Maps

In this paper, we tackle the problem of online road network extraction f...

Namdar Homayounfar, et al. ∙

research

∙ 06/15/2022

Variable Bitrate Neural Fields

Neural approximations of scalar and vector fields, such as signed distan...

Towaki Takikawa, et al. ∙

research

∙ 03/07/2019

Concurrent Meta Reinforcement Learning

State-of-the-art meta reinforcement learning algorithms typically assume...

Emilio Parisotto, et al. ∙

research

∙ 07/12/2019

Gated-SCNN: Gated Shape CNNs for Semantic Segmentation

Current state-of-the-art methods for image segmentation form a dense ima...

Towaki Takikawa, et al. ∙

research

∙ 08/03/2019

Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderer

Many machine learning models operate on images, but ignore the fact that...

Wenzheng Chen, et al. ∙

research

∙ 01/17/2020

A Derivative-Free 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...

Jihun Han, et al. ∙

research

∙ 01/16/2021

GeoSim: Realistic Video Simulation via Geometry-Aware Composition for Self-Driving

Scalable sensor simulation is an important yet challenging open problem ...

Yun Chen, et al. ∙

research

∙ 02/17/2020

BatchEnsemble: an Alternative Approach to Efficient Ensemble and Lifelong Learning

Ensembles, where multiple neural networks are trained individually and t...

Yeming Wen, et al. ∙

research

∙ 01/17/2021

Adversarial Attacks On Multi-Agent Communication

Growing at a very fast pace, modern autonomous systems will soon be depl...

James Tu, et al. ∙

research

∙ 03/20/2021

An Empirical Framework for Domain Generalization in Clinical Settings

Clinical machine learning models experience significantly degraded perfo...

Haoran Zhang, et al. ∙

research

∙ 11/13/2021

Introducing Variational Autoencoders to High School Students

Generative Artificial Intelligence (AI) models are a compelling way to i...

Zhuoyue Lyu, et al. ∙

research

∙ 01/12/2019

DeepSpline: Data-Driven Reconstruction of Parametric Curves and Surfaces

Reconstruction of geometry based on different input modes, such as image...

Jun Gao, et al. ∙

research

∙ 04/25/2019

Meta-Sim: Learning to Generate Synthetic Datasets

Training models to high-end performance requires availability of large l...

Amlan Kar, et al. ∙

research

∙ 06/23/2020

Experience Replay with Likelihood-free Importance Weights

The use of past experiences to accelerate temporal difference (TD) learn...

Samarth Sinha, et al. ∙

research

∙ 06/19/2018

Neural Ordinary Differential Equations

We introduce a new family of deep neural network models. Instead of spec...

Tian Qi Chen, et al. ∙

research

∙ 05/14/2020

W-Cell-Net: Multi-frame Interpolation of Cellular Microscopy Videos

Deep Neural Networks are increasingly used in video frame interpolation ...

Rohit Saha, et al. ∙

research

∙ 01/17/2021

Cost-Efficient Online Hyperparameter Optimization

Recent work on hyperparameters optimization (HPO) has shown the possibil...

Jingkang Wang, et al. ∙

research

∙ 03/24/2022

Effective Explanations for Entity Resolution Models

Entity resolution (ER) aims at matching records that refer to the same r...

Tommaso Teofili, et al. ∙

research

∙ 06/19/2022

Scalable Neural Data Server: A Data Recommender for Transfer Learning

Absence of large-scale labeled data in the practitioner's target domain ...

Tianshi Cao, et al. ∙

research

∙ 05/04/2019

Deep Multi-Sensor Lane Detection

Reliable and accurate lane detection has been a long-standing problem in...

Min Bai, et al. ∙

research

∙ 06/02/2020

Aligning Superhuman AI and Human Behavior: Chess as a Model System

As artificial intelligence becomes increasingly intelligent—in some case...

Reid McIlroy-Young, et al. ∙

research

∙ 08/02/2022

Detecting Individual Decision-Making Style: Exploring Behavioral Stylometry in Chess

The advent of machine learning models that surpass human decision-making...

Reid McIlroy-Young, et al. ∙

research

∙ 12/04/2018

SurfConv: Bridging 3D and 2D Convolution for RGBD Images

We tackle the problem of using 3D information in convolutional neural ne...

Hang Chu, et al. ∙

research

∙ 04/26/2021

Towards Good Practices for Efficiently Annotating Large-Scale Image Classification Datasets

Data is the engine of modern computer vision, which necessitates collect...

Yuan-Hong Liao, et al. ∙

research

∙ 10/14/2021

Augmenting Imitation Experience via Equivariant Representations

The robustness of visual navigation policies trained through imitation o...

Dhruv Sharma, et al. ∙

UNIVERSITY OF TORONTO

Featured Researchers