
Identifying Critical Neurons in ANN Architectures using Mixed Integer Programming
We introduce a novel approach to optimize the architecture of deep neura...
read it

SketchTransfer: A Challenging New Task for Exploring DetailInvariance and the Abstractions Learned by Deep Networks
Deep networks have achieved excellent results in perceptual tasks, yet t...
read it

Boosting Image Recognition with Nondifferentiable Constraints
In this paper, we study the problem of image recognition with nondiffer...
read it

Deep Verifier Networks: Verification of Deep Discriminative Models with Deep Generative Models
AI Safety is a major concern in many deep learning applications such as ...
read it

Selective Brain Damage: Measuring the Disparate Impact of Model Pruning
Neural network pruning techniques have demonstrated it is possible to re...
read it

GraphAF: a Flowbased Autoregressive Model for Molecular Graph Generation
Molecular graph generation is a fundamental problem for drug discovery a...
read it

Talk the Walk: Navigating New York City through Grounded Dialogue
We introduce "Talk The Walk", the first largescale dialogue dataset gro...
read it

Applying Knowledge Transfer for Water Body Segmentation in Peru
In this work, we present the application of convolutional neural network...
read it

The effect of task and training on intermediate representations in convolutional neural networks revealed with modified RV similarity analysis
Centered Kernel Alignment (CKA) was recently proposed as a similarity me...
read it

Painless Stochastic Gradient: Interpolation, LineSearch, and Convergence Rates
Recent works have shown that stochastic gradient descent (SGD) achieves ...
read it

Towards Understanding Generalization in GradientBased MetaLearning
In this work we study generalization of neural networks in gradientbase...
read it

Improved Conditional VRNNs for Video Prediction
Predicting future frames for a video sequence is a challenging generativ...
read it

Human Gait Symmetry Assessment using a Depth Camera and Mirrors
This paper proposes a reliable approach for human gait symmetry assessme...
read it

Neural Multisensory Scene Inference
For embodied agents to infer representations of the underlying 3D physic...
read it

RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space
We study the problem of learning representations of entities and relatio...
read it

Perceptual Generative Autoencoders
Modern generative models are usually designed to match target distributi...
read it

Detecting semantic anomalies
We critically appraise the recent interest in outofdistribution (OOD) ...
read it

Scattering GCN: Overcoming Oversmoothness in Graph Convolutional Networks
Graph convolutional networks (GCNs) have shown promising results in proc...
read it

GraphVite: A HighPerformance CPUGPU Hybrid System for Node Embedding
Learning continuous representations of nodes is attracting growing inter...
read it

GradientBased Neural DAG Learning
We propose a novel scorebased approach to learning a directed acyclic g...
read it

Straight to the Tree: Constituency Parsing with Neural Syntactic Distance
In this work, we propose a novel constituency parsing scheme. The model ...
read it

UNet FixedPoint Quantization for Medical Image Segmentation
Model quantization is leveraged to reduce the memory consumption and the...
read it

Nonnormal Recurrent Neural Network (nnRNN): learning long time dependencies while improving expressivity with transient dynamics
A recent strategy to circumvent the exploding and vanishing gradient pro...
read it

Building EndToEnd Dialogue Systems Using Generative Hierarchical Neural Network Models
We investigate the task of building open domain, conversational dialogue...
read it

Invariant Representations for Noisy Speech Recognition
Modern automatic speech recognition (ASR) systems need to be robust unde...
read it

A Hierarchical Latent Variable EncoderDecoder Model for Generating Dialogues
Sequential data often possesses a hierarchical structure with complex de...
read it

Revisiting Natural Gradient for Deep Networks
We evaluate natural gradient, an algorithm originally proposed in Amari ...
read it

Knowledge Matters: Importance of Prior Information for Optimization
We explore the effect of introducing prior information into the intermed...
read it

Multiresolution Recurrent Neural Networks: An Application to Dialogue Response Generation
We introduce the multiresolution recurrent neural network, which extends...
read it

On Training Deep Boltzmann Machines
The deep Boltzmann machine (DBM) has been an important development in th...
read it

Theano: new features and speed improvements
Theano is a linear algebra compiler that optimizes a user's symbolically...
read it

Iterative Alternating Neural Attention for Machine Reading
We propose a novel neural attention architecture to tackle machine compr...
read it

A Hierarchical Recurrent EncoderDecoder For Generative ContextAware Query Suggestion
Users may strive to formulate an adequate textual query for their inform...
read it

On the number of response regions of deep feed forward networks with piecewise linear activations
This paper explores the complexity of deep feedforward networks with lin...
read it

Neural Networks with Few Multiplications
For most deep learning algorithms training is notoriously time consuming...
read it

On the saddle point problem for nonconvex optimization
A central challenge to many fields of science and engineering involves m...
read it

A CharacterLevel Decoder without Explicit Segmentation for Neural Machine Translation
The existing machine translation systems, whether phrasebased or neural...
read it

Dynamic Layer Normalization for Adaptive Neural Acoustic Modeling in Speech Recognition
Layer normalization is a recently introduced technique for normalizing t...
read it

Recurrent Neural Networks With Limited Numerical Precision
Recurrent Neural Networks (RNNs) produce stateofart performance on man...
read it

Pylearn2: a machine learning research library
Pylearn2 is a machine learning research library. This does not just mean...
read it

ContextDependent Word Representation for Neural Machine Translation
We first observe a potential weakness of continuous vector representatio...
read it

How to Construct Deep Recurrent Neural Networks
In this paper, we explore different ways to extend a recurrent neural ne...
read it

Memory Augmented Neural Networks with Wormhole Connections
Recent empirical results on longterm dependency tasks have shown that n...
read it

Learning to Compute Word Embeddings On the Fly
Words in natural language follow a Zipfian distribution whereby some wor...
read it

Learning to Understand Phrases by Embedding the Dictionary
Distributional models that learn rich semantic word representations are ...
read it

Deep Complex Networks
At present, the vast majority of building blocks, techniques, and archit...
read it

An empirical analysis of dropout in piecewise linear networks
The recently introduced dropout training criterion for neural networks h...
read it

Noisy Activation Functions
Common nonlinear activation functions used in neural networks can cause ...
read it

An Empirical Investigation of Catastrophic Forgetting in GradientBased Neural Networks
Catastrophic forgetting is a problem faced by many machine learning mode...
read it

On the Challenges of Physical Implementations of RBMs
Restricted Boltzmann machines (RBMs) are powerful machine learning model...
read it
Université de Montréal
61278 The Université de Montréal is a Frenchlanguage public research university in Montreal, Quebec, Canada.