Brown University

research

∙ 04/28/2020

Streamlining Tensor and Network Pruning in PyTorch

In order to contrast the explosion in size of state-of-the-art machine l...

Michela Paganini, et al. ∙

research

∙ 07/10/2019

DeepXDE: A deep learning library for solving differential equations

Deep learning has achieved remarkable success in diverse applications; h...

Lu Lu, et al. ∙

research

∙ 05/27/2019

Quantifying the generalization error in deep learning in terms of data distribution and neural network smoothness

The accuracy of deep learning, i.e., deep neural networks, can be charac...

Pengzhan Jin, et al. ∙

research

∙ 12/05/2019

15 Keypoints Is All You Need

Pose tracking is an important problem that requires identifying unique h...

Michael Snower, et al. ∙

research

∙ 07/08/2022

Physics-Informed Deep Neural Operator Networks

Standard neural networks can approximate general nonlinear operators, re...

Somdatta Goswami, et al. ∙

research

∙ 11/16/2019

Unsupervised Deep Metric Learning via Auxiliary Rotation Loss

Deep metric learning is an important area due to its applicability to ma...

Xuefei Cao, et al. ∙

research

∙ 08/09/2022

Continual Prune-and-Select: Class-incremental learning with specialized subnetworks

The human brain is capable of learning tasks sequentially mostly without...

Aleksandr Dekhovich, et al. ∙

research

∙ 01/18/2019

Theory of Minds: Understanding Behavior in Groups Through Inverse Planning

Human social behavior is structured by relationships. We form teams, gro...

Michael Shum, et al. ∙

research

∙ 05/16/2022

Scalable algorithms for physics-informed neural and graph networks

Physics-informed machine learning (PIML) has emerged as a promising new ...

Khemraj Shukla, et al. ∙

research

∙ 03/09/2022

On the influence of over-parameterization in manifold based surrogates and deep neural operators

Constructing accurate and generalizable approximators for complex physic...

Katiana Kontolati, et al. ∙

research

∙ 01/19/2022

Scotch: An Efficient Secure Computation Framework for Secure Aggregation

Federated learning enables multiple data owners to jointly train a machi...

Arup Mondal, et al. ∙

research

∙ 11/01/2021

On the Expressivity of Markov Reward

Reward is the driving force for reinforcement-learning agents. This pape...

David Abel, et al. ∙

research

∙ 01/31/2019

Successor Features Support Model-based and Model-free Reinforcement Learning

One key challenge in reinforcement learning is the ability to generalize...

Lucas Lehnert, et al. ∙

research

∙ 12/13/2021

Learning Body-Aware 3D Shape Generative Models

The shape of many objects in the built environment is dictated by their ...

Bryce Blinn, et al. ∙

research

∙ 12/08/2019

Individual predictions matter: Assessing the effect of data ordering in training fine-tuned CNNs for medical imaging

We reproduced the results of CheXNet with fixed hyperparameters and 50 d...

John R. Zech, et al. ∙

research

∙ 12/05/2020

Learning Poisson systems and trajectories of autonomous systems via Poisson neural networks

We propose the Poisson neural networks (PNNs) to learn Poisson systems a...

Pengzhan Jin, et al. ∙

research

∙ 04/06/2021

A Caputo fractional derivative-based algorithm for optimization

We propose a novel Caputo fractional derivative-based optimization algor...

Yeonjong Shin, et al. ∙

research

∙ 03/14/2019

Teaching with IMPACT

Like many problems in AI in their general form, supervised learning is c...

Carl Trimbach, et al. ∙

research

∙ 08/24/2020

Solving Inverse Stochastic Problems from Discrete Particle Observations Using the Fokker-Planck Equation and Physics-informed Neural Networks

The Fokker-Planck (FP) equation governing the evolution of the probabili...

Xiaoli Chen, et al. ∙

research

∙ 09/13/2021

Shape-Biased Domain Generalization via Shock Graph Embeddings

There is an emerging sense that the vulnerability of Image Convolutional...

Maruthi Narayanan, et al. ∙

research

∙ 11/07/2021

Look at the Variance! Efficient Black-box Explanations with Sobol-based Sensitivity Analysis

We describe a novel attribution method which is grounded in Sensitivity ...

Thomas Fel, et al. ∙

research

∙ 09/23/2019

PPINN: Parareal Physics-Informed Neural Network for time-dependent PDEs

Physics-informed neural networks (PINNs) encode physical conservation la...

Xuhui Meng, et al. ∙

research

∙ 12/09/2021

Learning Generalizable Behavior via Visual Rewrite Rules

Though deep reinforcement learning agents have achieved unprecedented su...

Yiheng Xie, et al. ∙

research

∙ 05/17/2022

Function Regression using Spiking DeepONet

One of the main broad applications of deep learning is function regressi...

Adar Kahana, et al. ∙

research

∙ 02/13/2020

The Efficiency of Human Cognition Reflects Planned Information Processing

Planning is useful. It lets people take actions that have desirable long...

Mark K Ho, et al. ∙

research

∙ 04/15/2020

Wasserstein Adversarial Autoencoders for Knowledge Graph Embedding based Drug-Drug Interaction Prediction

Interaction between pharmacological agents can trigger unexpected advers...

Yuanfei Dai, et al. ∙

research

∙ 06/23/2020

Robot Object Retrieval with Contextual Natural Language Queries

Natural language object retrieval is a highly useful yet challenging tas...

Thao Nguyen, et al. ∙

research

∙ 10/29/2020

Recurrent neural circuits for contour detection

We introduce a deep recurrent neural network architecture that approxima...

Drew Linsley, et al. ∙

research

∙ 07/12/2021

Meta-learning PINN loss functions

We propose a meta-learning technique for offline discovery of physics-in...

Apostolos F Psaros, et al. ∙

research

∙ 08/16/2021

AdaCon: Adaptive Context-Aware Object Detection for Resource-Constrained Embedded Devices

Convolutional Neural Networks achieve state-of-the-art accuracy in objec...

Marina Neseem, et al. ∙

research

∙ 09/28/2021

DynG2G: An Efficient Stochastic Graph Embedding Method for Temporal Graphs

Dynamic graph embedding has gained great attention recently due to its c...

Mengjia Xu, et al. ∙

research

∙ 12/29/2021

On the Instability of Relative Pose Estimation and RANSAC's Role

In this paper we study the numerical instabilities of the 5- and 7-point...

Hongyi Fan, et al. ∙

research

∙ 03/21/2022

Learning robot motor skills with mixed reality

Mixed Reality (MR) has recently shown great success as an intuitive inte...

Eric Rosen, et al. ∙

research

∙ 05/03/2019

Learning in Modal Space: Solving Time-Dependent Stochastic PDEs Using Physics-Informed Neural Networks

One of the open problems in scientific computing is the long-time integr...

Dongkun Zhang, et al. ∙

research

∙ 08/23/2019

Stackelberg Punishment and Bully-Proofing Autonomous Vehicles

Mutually beneficial behavior in repeated games can be enforced via the t...

Matt Cooper, et al. ∙

research

∙ 05/27/2021

Tracking Without Re-recognition in Humans and Machines

Imagine trying to track one particular fruitfly in a swarm of hundreds. ...

Drew Linsley, et al. ∙

research

∙ 08/12/2021

HAC Explore: Accelerating Exploration with Hierarchical Reinforcement Learning

Sparse rewards and long time horizons remain challenging for reinforceme...

Willie McClinton, et al. ∙

research

∙ 07/19/2019

Interactive Learning of Environment Dynamics for Sequential Tasks

In order for robots and other artificial agents to efficiently learn to ...

Robert Loftin, et al. ∙

research

∙ 01/12/2021

Bootstrapping Motor Skill Learning with Motion Planning

Learning a robot motor skill from scratch is impractically slow; so much...

Ben Abbatematteo, et al. ∙

research

∙ 04/20/2022

Deep transfer learning for partial differential equations under conditional shift with DeepONet

Traditional machine learning algorithms are designed to learn in isolati...

Somdatta Goswami, et al. ∙

research

∙ 06/20/2022

The Fallacy of AI Functionality

Deployed AI systems often do not work. They can be constructed haphazard...

Inioluwa Deborah Raji, et al. ∙

research

∙ 10/16/2018

Finding Options that Minimize Planning Time

While adding temporally abstract actions, or options, to an agent's acti...

Yuu Jinnai, et al. ∙

research

∙ 07/23/2019

Trainability and Data-dependent Initialization of Over-parameterized ReLU Neural Networks

A neural network is said to be over-specified if its representational po...

Yeonjong Shin, et al. ∙

research

∙ 08/29/2019

Potential Flow Generator with L_2 Optimal Transport Regularity for Generative Models

We propose a potential flow generator with L_2 optimal transport regular...

Liu Yang, et al. ∙

research

∙ 10/15/2020

Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Grounding

We introduce Room-Across-Room (RxR), a new Vision-and-Language Navigatio...

Alexander Ku, et al. ∙

research

∙ 10/29/2021

BitTrain: Sparse Bitmap Compression for Memory-Efficient Training on the Edge

Training on the Edge enables neural networks to learn continuously from ...

Abdelrahman Hosny, et al. ∙

research

∙ 12/16/2021

CODER: An efficient framework for improving retrieval through COntextualized Document Embedding Reranking

We present a framework for improving the performance of a wide class of ...

George Zerveas, et al. ∙

research

∙ 02/11/2022

Assessing Privacy Risks from Feature Vector Reconstruction Attacks

In deep neural networks for facial recognition, feature vectors are nume...

Emily Wenger, et al. ∙

research

∙ 02/17/2020

A survey of statistical learning techniques as applied to inexpensive pediatric Obstructive Sleep Apnea data

Pediatric obstructive sleep apnea affects an estimated 1-5 elementary-sc...

Emily T. Winn, et al. ∙

research

∙ 06/04/2022

Interpolating Between Softmax Policy Gradient and Neural Replicator Dynamics with Capped Implicit Exploration

Neural replicator dynamics (NeuRD) is an alternative to the foundational...

Dustin Morrill, et al. ∙

Brown University

Featured Researchers