
MatrixNets: A New Scale and Aspect Ratio Aware Architecture for Object Detection
We present MatrixNets (xNets), a new deep architecture for object detect...
read it

Multi Type Mean Field Reinforcement Learning
Mean field theory provides an effective way of scaling multiagent reinfo...
read it

Batch norm with entropic regularization turns deterministic autoencoders into generative models
The variational autoencoder is a well defined deep generative model that...
read it

Optimality and Stability in NonConvexNonConcave MinMax Optimization
Convergence to a saddle point for convexconcave functions has been stud...
read it

Generative Mixture of Networks
A generative model based on training deep architectures is proposed. The...
read it

Online Structure Learning for SumProduct Networks with Gaussian Leaves
Sumproduct networks have recently emerged as an attractive representati...
read it

A Unified Approach for Learning the Parameters of SumProduct Networks
We present a unified approach for learning the parameters of SumProduct...
read it

Online and Distributed learning of Gaussian mixture models by Bayesian Moment Matching
The Gaussian mixture model is a classic technique for clustering and dat...
read it

Exploiting Structure in Weighted Model Counting Approaches to Probabilistic Inference
Previous studies have demonstrated that encoding a Bayesian network into...
read it

Dynamic Sum Product Networks for Tractable Inference on Sequence Data (Extended Version)
SumProduct Networks (SPN) have recently emerged as a new class of tract...
read it

ValueDirected Belief State Approximation for POMDPs
We consider the problem beliefstate monitoring for the purposes of impl...
read it

ValueDirected Sampling Methods for POMDPs
We consider the problem of approximate beliefstate monitoring using par...
read it

Vectorspace Analysis of Beliefstate Approximation for POMDPs
We propose a new approach to valuedirected belief state approximation f...
read it

On the Relationship between SumProduct Networks and Bayesian Networks
In this paper, we establish some theoretical connections between SumPro...
read it

Hierarchical POMDP Controller Optimization by Likelihood Maximization
Planning can often be simpli ed by decomposing the task into smaller tas...
read it

Comparative Analysis of Probabilistic Models for Activity Recognition with an Instrumented Walker
Rollating walkers are popular mobility aids used by older adults to impr...
read it

Deep Active Learning for Dialogue Generation
We propose an online, endtoend, neural generative conversational model...
read it

Discovering Conversational Dependencies between Messages in Dialogs
We investigate the task of inferring conversational dependencies between...
read it

SelfAdaptive Hierarchical Sentence Model
The ability to accurately model a sentence at varying stages (e.g., word...
read it

OrderPlanning Neural Text Generation From Structured Data
Generating texts from structured data (e.g., a table) is important for v...
read it

Why Do Neural Dialog Systems Generate Short and Meaningless Replies? A Comparison between Dialog and Translation
This paper addresses the question: Why do neural dialog systems generate...
read it

Affective Neural Response Generation
Existing neural conversational models process natural language primarily...
read it

Variational Attention for SequencetoSequence Models
The variational encoderdecoder (VED) encodes source information as a se...
read it

On Improving Deep Reinforcement Learning for POMDPs
Deep Reinforcement Learning (RL) recently emerged as one of the most com...
read it

Unsupervised Video Object Segmentation for Deep Reinforcement Learning
We present a new technique for deep reinforcement learning that automati...
read it

Progressive Memory Banks for Incremental Domain Adaptation
This paper addresses the problem of incremental domain adaptation (IDA)....
read it

SPFlow: An Easy and Extensible Library for Deep Probabilistic Learning using SumProduct Networks
We introduce SPFlow, an opensource Python library providing a simple in...
read it

Relational Representation Learning for Dynamic (Knowledge) Graphs: A Survey
Graphs arise naturally in many realworld applications including social ...
read it

Time2Vec: Learning a Vector Representation of Time
Time is an important feature in many applications involving events that ...
read it

Comparing EM with GD in Mixture Models of Two Components
The expectationmaximization (EM) algorithm has been widely used in mini...
read it

Diachronic Embedding for Temporal Knowledge Graph Completion
Knowledge graphs (KGs) typically contain temporal facts indicating relat...
read it

Matrix Nets: A New Deep Architecture for Object Detection
We present Matrix Nets (xNets), a new deep architecture for object detec...
read it

Unsupervised Multilingual Alignment using Wasserstein Barycenter
We study unsupervised multilingual alignment, the problem of finding wor...
read it

Complete Hierarchy of Relaxation for Constrained Signomial Positivity
In this article, we prove that the SumsofAM/GM Exponential (SAGE) rela...
read it

Learning Dynamic Knowledge Graphs to Generalize on TextBased Games
Playing textbased games requires skill in processing natural language a...
read it

Generating Emotionally Aligned Responses in Dialogues using Affect Control Theory
Stateoftheart neural dialogue systems excel at syntactic and semantic...
read it
Pascal Poupart
is this you? claim profile
Full Professor in Artificial Intelligence, Machine Learning, Health Informatics at David R. Cheriton School of Computer Science University of Waterloo, Associate Dditor of the Journal of Artificial Intelligence Research (JAIR), Member of the editorial board of the Journal of Machine Learning Research (JMLR), Guest Editor for the Machine Learning Journal (MLJ), Cheriton Faculty Fellowship (20152018), best student paper honourable mention (SAT2017), outstanding collaborator award from Huawei Noah's Ark (2016), a top reviewer award (ICML2016), the best main track solver and best application solver (SAT2016 competition), a best reviewer award (NIPS2015), an Early Researcher Award from the Ontario Ministry of Research and Innovation (2008), two Google reserch awards (20072008), a best paper award runner up (UAI2008) and the IAPR best paper award (ICVS2007),