
Streamlining Tensor and Network Pruning in PyTorch
In order to contrast the explosion in size of stateoftheart machine l...
read it

DeepXDE: A deep learning library for solving differential equations
Deep learning has achieved remarkable success in diverse applications; h...
read it

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...
read it

15 Keypoints Is All You Need
Pose tracking is an important problem that requires identifying unique h...
read it

Unsupervised Deep Metric Learning via Auxiliary Rotation Loss
Deep metric learning is an important area due to its applicability to ma...
read it

Theory of Minds: Understanding Behavior in Groups Through Inverse Planning
Human social behavior is structured by relationships. We form teams, gro...
read it

Successor Features Support Modelbased and Modelfree Reinforcement Learning
One key challenge in reinforcement learning is the ability to generalize...
read it

Individual predictions matter: Assessing the effect of data ordering in training finetuned CNNs for medical imaging
We reproduced the results of CheXNet with fixed hyperparameters and 50 d...
read it

Learning Poisson systems and trajectories of autonomous systems via Poisson neural networks
We propose the Poisson neural networks (PNNs) to learn Poisson systems a...
read it

Teaching with IMPACT
Like many problems in AI in their general form, supervised learning is c...
read it

Solving Inverse Stochastic Problems from Discrete Particle Observations Using the FokkerPlanck Equation and Physicsinformed Neural Networks
The FokkerPlanck (FP) equation governing the evolution of the probabili...
read it

PPINN: Parareal PhysicsInformed Neural Network for timedependent PDEs
Physicsinformed neural networks (PINNs) encode physical conservation la...
read it

The Efficiency of Human Cognition Reflects Planned Information Processing
Planning is useful. It lets people take actions that have desirable long...
read it

Wasserstein Adversarial Autoencoders for Knowledge Graph Embedding based DrugDrug Interaction Prediction
Interaction between pharmacological agents can trigger unexpected advers...
read it

Robot Object Retrieval with Contextual Natural Language Queries
Natural language object retrieval is a highly useful yet challenging tas...
read it

Recurrent neural circuits for contour detection
We introduce a deep recurrent neural network architecture that approxima...
read it

Learning in Modal Space: Solving TimeDependent Stochastic PDEs Using PhysicsInformed Neural Networks
One of the open problems in scientific computing is the longtime integr...
read it

Stackelberg Punishment and BullyProofing Autonomous Vehicles
Mutually beneficial behavior in repeated games can be enforced via the t...
read it

Interactive Learning of Environment Dynamics for Sequential Tasks
In order for robots and other artificial agents to efficiently learn to ...
read it

Bootstrapping Motor Skill Learning with Motion Planning
Learning a robot motor skill from scratch is impractically slow; so much...
read it

Finding Options that Minimize Planning Time
While adding temporally abstract actions, or options, to an agent's acti...
read it

Trainability and Datadependent Initialization of Overparameterized ReLU Neural Networks
A neural network is said to be overspecified if its representational po...
read it

Potential Flow Generator with L_2 Optimal Transport Regularity for Generative Models
We propose a potential flow generator with L_2 optimal transport regular...
read it

RoomAcrossRoom: Multilingual VisionandLanguage Navigation with Dense Spatiotemporal Grounding
We introduce RoomAcrossRoom (RxR), a new VisionandLanguage Navigatio...
read it

A survey of statistical learning techniques as applied to inexpensive pediatric Obstructive Sleep Apnea data
Pediatric obstructive sleep apnea affects an estimated 15 elementarysc...
read it

Automatic Discovery and Optimization of Parts for Image Classification
Partbased representations have been shown to be very useful for image c...
read it

Joint and conditional estimation of tagging and parsing models
This paper compares two different ways of estimating statistical languag...
read it

Explaining away ambiguity: Learning verb selectional preference with Bayesian networks
This paper presents a Bayesian model for unsupervised learning of verb s...
read it

Learning Robust Dialog Policies in Noisy Environments
Modern virtual personal assistants provide a convenient interface for co...
read it

Implementing the Deep QNetwork
The Deep QNetwork proposed by Mnih et al. [2015] has become a benchmark...
read it

An Improved Training Procedure for Neural Autoregressive Data Completion
Neural autoregressive models are explicit density estimators that achiev...
read it

Deep Abstract QNetworks
We examine the problem of learning and planning on highdimensional doma...
read it

HardwareSoftware Codesign of Accurate, Multiplierfree Deep Neural Networks
While Deep Neural Networks (DNNs) push the stateoftheart in many mach...
read it

Summable Reparameterizations of Wasserstein Critics in the OneDimensional Setting
Generative adversarial networks (GANs) are an exciting alternative to al...
read it

Active Exploration for Learning Symbolic Representations
We introduce an online active exploration algorithm for dataefficiently...
read it

Mean Actor Critic
We propose a new algorithm, Mean ActorCritic (MAC), for discreteaction...
read it

Understanding the Impact of Precision Quantization on the Accuracy and Energy of Neural Networks
Deep neural networks are gaining in popularity as they are used to gener...
read it

Learning to Infer Graphics Programs from HandDrawn Images
We introduce a model that learns to convert simple hand drawings into gr...
read it

Runtime Configurable Deep Neural Networks for EnergyAccuracy Tradeoff
We present a novel dynamic configuration technique for deep neural netwo...
read it

Robust and Efficient Transfer Learning with HiddenParameter Markov Decision Processes
We introduce a new formulation of the Hidden Parameter Markov Decision P...
read it

Hybrid Code Networks: practical and efficient endtoend dialog control with supervised and reinforcement learning
Endtoend learning of recurrent neural networks (RNNs) is an attractive...
read it

Near Optimal Behavior via Approximate State Abstraction
The combinatorial explosion that plagues planning and reinforcement lear...
read it

AgentAgnostic HumanintheLoop Reinforcement Learning
Providing Reinforcement Learning agents with expert advice can dramatica...
read it

Sampleefficient Deep Reinforcement Learning for Dialog Control
Representing a dialog policy as a recurrent neural network (RNN) is attr...
read it

The Surfacing of Multiview 3D Drawings via Lofting and Occlusion Reasoning
The threedimensional reconstruction of scenes from multiple views has m...
read it

Transfer Learning Across Patient Variations with Hidden Parameter Markov Decision Processes
Due to physiological variation, patients diagnosed with the same conditi...
read it

Parametric Gaussian Process Regression for Big Data
This work introduces the concept of parametric Gaussian processes (PGPs)...
read it

Fast Learning of Clusters and Topics via Sparse Posteriors
Mixture models and topic models generate each observation from a single ...
read it

Critical Contours: An Invariant Linking Image Flow with Salient Surface Organization
We exploit a key result from visual psychophysics  that individuals pe...
read it

Embedding Projector: Interactive Visualization and Interpretation of Embeddings
Embeddings are ubiquitous in machine learning, appearing in recommender ...
read it
Brown University
Brown University is a private Ivy League research university in Providence, Rhode Island, United States.