Publications (95)
Learning Neural Causal Models from Unknown Interventions
Nan Rosemary Ke, Olexa Bilaniuk, Anirudh Goyal +6
Promising results have driven a recent surge of interest in continuous optimization methods for Bayesian network structure learning from observational data. However, there are theo…
ReviewerToo: Should AI Join The Program Committee? A Look At The Future of Peer Review
Gaurav Sahu, Hugo Larochelle, Laurent Charlin +1
Peer review is the cornerstone of scientific publishing, yet it suffers from inconsistencies, reviewer subjectivity, and scalability challenges. We introduce ReviewerToo, a modular…
Head2Toe: Utilizing Intermediate Representations for Better Transfer Learning
Utku Evci, Vincent Dumoulin, Hugo Larochelle +1
Transfer-learning methods aim to improve performance in a data-scarce target domain using a model pretrained on a data-rich source domain. A cost-efficient strategy, linear probing…
Teaching Algorithmic Reasoning via In-context Learning
Hattie Zhou, Azade Nova, Hugo Larochelle +3
Large language models (LLMs) have shown increasing in-context learning capabilities through scaling up model and data size. Despite this progress, LLMs are still unable to solve al…
Learning to Execute Programs with Instruction Pointer Attention Graph Neural Networks
David Bieber, Charles Sutton, Hugo Larochelle +1
Graph neural networks (GNNs) have emerged as a powerful tool for learning software engineering tasks including code completion, bug finding, and program repair. They benefit from l…
Learning Multilingual Word Representations using a Bag-of-Words Autoencoder
Stanislas Lauly, Alex Boulanger, Hugo Larochelle
Recent work on learning multilingual word representations usually relies on the use of word-level alignements (e.g. infered with the help of GIZA++) between translated sentences, i…
Bringing SAM to new heights: Leveraging elevation data for tree crown segmentation from drone imagery
Mélisande Teng, Arthur Ouaknine, Etienne Laliberté +3
Information on trees at the individual level is crucial for monitoring forest ecosystems and planning forest management. Current monitoring methods involve ground measurements, req…
Many-Shot In-Context Learning
Rishabh Agarwal, Avi Singh, Lei M. Zhang +12
Large language models (LLMs) excel at few-shot in-context learning (ICL) -- learning from a few examples provided in context at inference, without any weight updates. Newly expande…
Blindfold Baselines for Embodied QA
Ankesh Anand, Eugene Belilovsky, Kyle Kastner +2
We explore blindfold (question-only) baselines for Embodied Question Answering. The EmbodiedQA task requires an agent to answer a question by intelligently navigating in a simulate…
Comparing Transfer and Meta Learning Approaches on a Unified Few-Shot Classification Benchmark
Vincent Dumoulin, Neil Houlsby, Utku Evci +4
Meta and transfer learning are two successful families of approaches to few-shot learning. Despite highly related goals, state-of-the-art advances in each family are measured large…
A density estimation perspective on learning from pairwise human preferences
Vincent Dumoulin, Daniel D. Johnson, Pablo Samuel Castro +2
Learning from human feedback (LHF) -- and in particular learning from pairwise preferences -- has recently become a crucial ingredient in training large language models (LLMs), and…
Document Neural Autoregressive Distribution Estimation
Stanislas Lauly, Yin Zheng, Alexandre Allauzen +1
We present an approach based on feed-forward neural networks for learning the distribution of textual documents. This approach is inspired by the Neural Autoregressive Distribution…
Learning a Universal Template for Few-shot Dataset Generalization
Eleni Triantafillou, Hugo Larochelle, Richard Zemel +1
Few-shot dataset generalization is a challenging variant of the well-studied few-shot classification problem where a diverse training set of several datasets is given, for the purp…
Deep Learning with Coherent Nanophotonic Circuits
Yichen Shen, Nicholas C. Harris, Scott Skirlo +8
Artificial Neural Networks are computational network models inspired by signal processing in the brain. These models have dramatically improved the performance of many learning tas…
Within-Brain Classification for Brain Tumor Segmentation
Mohammad Havaei, Hugo Larochelle, Philippe Poulin +1
Purpose: In this paper, we investigate a framework for interactive brain tumor segmentation which, at its core, treats the problem of interactive brain tumor segmentation as a mach…
Deep learning trends for focal brain pathology segmentation in MRI
Mohammad Havaei, Nicolas Guizard, Hugo Larochelle +1
Segmentation of focal (localized) brain pathologies such as brain tumors and brain lesions caused by multiple sclerosis and ischemic strokes are necessary for medical diagnosis, su…
Fortuitous Forgetting in Connectionist Networks
Hattie Zhou, Ankit Vani, Hugo Larochelle +1
Forgetting is often seen as an unwanted characteristic in both human and machine learning. However, we propose that forgetting can in fact be favorable to learning. We introduce "f…
CISO: Species Distribution Modeling Conditioned on Incomplete Species Observations
Hager Radi Abdelwahed, Mélisande Teng, Robin Zbinden +4
Species distribution models (SDMs) are widely used to predict species' geographic distributions, serving as critical tools for ecological research and conservation planning. Typica…
Dynamic Capacity Networks
Amjad Almahairi, Nicolas Ballas, Tim Cooijmans +3
We introduce the Dynamic Capacity Network (DCN), a neural network that can adaptively assign its capacity across different portions of the input data. This is achieved by combining…
Correlational Neural Networks
Sarath Chandar, Mitesh M. Khapra, Hugo Larochelle +1
Common Representation Learning (CRL), wherein different descriptions (or views) of the data are embedded in a common subspace, is receiving a lot of attention recently. Two popular…
An Infinite Restricted Boltzmann Machine
Marc-Alexandre Côté, Hugo Larochelle
We present a mathematical construction for the restricted Boltzmann machine (RBM) that doesn't require specifying the number of hidden units. In fact, the hidden layer size is adap…
Curriculum By Smoothing
Samarth Sinha, Animesh Garg, Hugo Larochelle
Convolutional Neural Networks (CNNs) have shown impressive performance in computer vision tasks such as image classification, detection, and segmentation. Moreover, recent work in…
Movie Description
Anna Rohrbach, Atousa Torabi, Marcus Rohrbach +5
Audio Description (AD) provides linguistic descriptions of movies and allows visually impaired people to follow a movie along with their peers. Such descriptions are by design main…
Autoencoding beyond pixels using a learned similarity metric
Anders Boesen Lindbo Larsen, Søren Kaae Sønderby, Hugo Larochelle +1
We present an autoencoder that leverages learned representations to better measure similarities in data space. By combining a variational autoencoder with a generative adversarial…
Practical Bayesian Optimization of Machine Learning Algorithms
Jasper Snoek, Hugo Larochelle, Ryan P. Adams
Machine learning algorithms frequently require careful tuning of model hyperparameters, regularization terms, and optimization parameters. Unfortunately, this tuning is often a "bl…
Towards Sustainable Investment Policies Informed by Opponent Shaping
Juan Agustin Duque, Razvan Ciuca, Ayoub Echchahed +2
Addressing climate change requires global coordination, yet rational economic actors often prioritize immediate gains over collective welfare, resulting in social dilemmas. InvestE…
A Supervised Neural Autoregressive Topic Model for Simultaneous Image Classification and Annotation
Yin Zheng, Yu-Jin Zhang, Hugo Larochelle
Topic modeling based on latent Dirichlet allocation (LDA) has been a framework of choice to perform scene recognition and annotation. Recently, a new type of topic model called the…
Self-Supervised Equivariant Scene Synthesis from Video
Cinjon Resnick, Or Litany, Cosmas Heià +3
We propose a self-supervised framework to learn scene representations from video that are automatically delineated into background, characters, and their animations. Our method cap…
Small-GAN: Speeding Up GAN Training Using Core-sets
Samarth Sinha, Han Zhang, Anirudh Goyal +3
Recent work by Brock et al. (2018) suggests that Generative Adversarial Networks (GANs) benefit disproportionately from large mini-batch sizes. Unfortunately, using large batches i…
Bird Distribution Modelling using Remote Sensing and Citizen Science data
Mélisande Teng, Amna Elmustafa, Benjamin Akera +2
Climate change is a major driver of biodiversity loss, changing the geographic range and abundance of many species. However, there remain significant knowledge gaps about the distr…
Describing Videos by Exploiting Temporal Structure
Li Yao, Atousa Torabi, Kyunghyun Cho +4
Recent progress in using recurrent neural networks (RNNs) for image description has motivated the exploration of their application for video description. However, while images are…
Impact of Aliasing on Generalization in Deep Convolutional Networks
Cristina Vasconcelos, Hugo Larochelle, Vincent Dumoulin +3
We investigate the impact of aliasing on generalization in Deep Convolutional Networks and show that data augmentation schemes alone are unable to prevent it due to structural limi…
Identifying birdsong syllables without labelled data
Mélisande Teng, Julien Boussard, David Rolnick +1
Identifying sequences of syllables within birdsongs is key to tackling a wide array of challenges, including bird individual identification and better understanding of animal commu…
The Hanabi Challenge: A New Frontier for AI Research
Nolan Bard, Jakob N. Foerster, Sarath Chandar +12
From the early days of computing, games have been important testbeds for studying how well machines can do sophisticated decision making. In recent years, machine learning has made…
InfoBot: Transfer and Exploration via the Information Bottleneck
Anirudh Goyal, Riashat Islam, Daniel Strouse +5
A central challenge in reinforcement learning is discovering effective policies for tasks where rewards are sparsely distributed. We postulate that in the absence of useful reward…
Your GAN is Secretly an Energy-based Model and You Should use Discriminator Driven Latent Sampling
Tong Che, Ruixiang Zhang, Jascha Sohl-Dickstein +4
We show that the sum of the implicit generator log-density of a GAN with the logit score of the discriminator defines an energy function which yields the true data densi…
Domain-Adversarial Training of Neural Networks
Yaroslav Ganin, Evgeniya Ustinova, Hana Ajakan +5
We introduce a new representation learning approach for domain adaptation, in which data at training and test time come from similar but different distributions. Our approach is di…
A Deep and Autoregressive Approach for Topic Modeling of Multimodal Data
Yin Zheng, Yu-Jin Zhang, Hugo Larochelle
Topic modeling based on latent Dirichlet allocation (LDA) has been a framework of choice to deal with multimodal data, such as in image annotation tasks. Another popular approach t…
Assessing SAM for Tree Crown Instance Segmentation from Drone Imagery
Mélisande Teng, Arthur Ouaknine, Etienne Laliberté +3
The potential of tree planting as a natural climate solution is often undermined by inadequate monitoring of tree planting projects. Current monitoring methods involve measuring tr…
Revisiting Fundamentals of Experience Replay
William Fedus, Prajit Ramachandran, Rishabh Agarwal +4
Experience replay is central to off-policy algorithms in deep reinforcement learning (RL), but there remain significant gaps in our understanding. We therefore present a systematic…
Diversity inducing Information Bottleneck in Model Ensembles
Samarth Sinha, Homanga Bharadhwaj, Anirudh Goyal +3
Although deep learning models have achieved state-of-the-art performance on a number of vision tasks, generalization over high dimensional multi-modal data, and reliable predictive…
An Effective Anti-Aliasing Approach for Residual Networks
Cristina Vasconcelos, Hugo Larochelle, Vincent Dumoulin +2
Image pre-processing in the frequency domain has traditionally played a vital role in computer vision and was even part of the standard pipeline in the early days of deep learning.…
Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples
Eleni Triantafillou, Tyler Zhu, Vincent Dumoulin +8
Few-shot classification refers to learning a classifier for new classes given only a few examples. While a plethora of models have emerged to tackle it, we find the procedure and d…
Brain Tumor Segmentation with Deep Neural Networks
Mohammad Havaei, Axel Davy, David Warde-Farley +6
In this paper, we present a fully automatic brain tumor segmentation method based on Deep Neural Networks (DNNs). The proposed networks are tailored to glioblastomas (both low and…
Hierarchical Memory Networks
Sarath Chandar, Sungjin Ahn, Hugo Larochelle +3
Memory networks are neural networks with an explicit memory component that can be both read and written to by the network. The memory is often addressed in a soft way using a softm…
A Deep and Tractable Density Estimator
Benigno Uria, Iain Murray, Hugo Larochelle
The Neural Autoregressive Distribution Estimator (NADE) and its real-valued version RNADE are competitive density models of multidimensional data across a variety of domains. These…
Repository-Level Prompt Generation for Large Language Models of Code
Disha Shrivastava, Hugo Larochelle, Daniel Tarlow
With the success of large language models (LLMs) of code and their use as code assistants (e.g. Codex used in GitHub Copilot), techniques for introducing domain-specific knowledge…
Neural Autoregressive Distribution Estimation
Benigno Uria, Marc-Alexandre Côté, Karol Gregor +2
We present Neural Autoregressive Distribution Estimation (NADE) models, which are neural network architectures applied to the problem of unsupervised distribution and density estim…
The Alien Space of Science: Sampling Coherent but Cognitively Unavailable Research Directions
Alejandro H. Artiles, Martin Weiss, Levin Brinkmann +6
Scientific discovery is constrained not only by what is true, but by what is cognitively available to the researchers currently exploring a field. Many directions are coherent in l…
Loss-sensitive Training of Probabilistic Conditional Random Fields
Maksims N. Volkovs, Hugo Larochelle, Richard S. Zemel
We consider the problem of training probabilistic conditional random fields (CRFs) in the context of a task where performance is measured using a specific loss function. While maxi…
Detoxifying LLMs via Representation Erasure-Based Preference Optimization
Nazanin Mohammadi Sepahvand, Eleni Triantafillou, Hugo Larochelle +3
Large language models (LLMs) trained on webscale data can produce toxic outputs, raising concerns for safe deployment. Prior defenses, based on applications of DPO, NPO, and simila…
Improving Reproducibility in Machine Learning Research (A Report from the NeurIPS 2019 Reproducibility Program)
Joelle Pineau, Philippe Vincent-Lamarre, Koustuv Sinha +5
One of the challenges in machine learning research is to ensure that presented and published results are sound and reliable. Reproducibility, that is obtaining similar results as p…
Don't flatten, tokenize! Unlocking the key to SoftMoE's efficacy in deep RL
Ghada Sokar, Johan Obando-Ceron, Aaron Courville +2
The use of deep neural networks in reinforcement learning (RL) often suffers from performance degradation as model size increases. While soft mixtures of experts (SoftMoEs) have re…
Algorithmic Improvements for Deep Reinforcement Learning applied to Interactive Fiction
Vishal Jain, William Fedus, Hugo Larochelle +2
Text-based games are a natural challenge domain for deep reinforcement learning algorithms. Their state and action spaces are combinatorially large, their reward function is sparse…
Capturing Individual Human Preferences with Reward Features
André Barreto, Vincent Dumoulin, Yiran Mao +6
Reinforcement learning from human feedback usually models preferences using a reward function that does not distinguish between people. We argue that this is unlikely to be a good…
Recall Traces: Backtracking Models for Efficient Reinforcement Learning
Anirudh Goyal, Philemon Brakel, William Fedus +5
In many environments only a tiny subset of all states yield high reward. In these cases, few of the interactions with the environment provide a relevant learning signal. Hence, we…
Conditional Restricted Boltzmann Machines for Structured Output Prediction
Volodymyr Mnih, Hugo Larochelle, Geoffrey E. Hinton
Conditional Restricted Boltzmann Machines (CRBMs) are rich probabilistic models that have recently been applied to a wide range of problems, including collaborative filtering, clas…
Domain-Adversarial Neural Networks
Hana Ajakan, Pascal Germain, Hugo Larochelle +2
We introduce a new representation learning algorithm suited to the context of domain adaptation, in which data at training and test time come from similar but different distributio…
The Search for Squawk: Agile Modeling in Bioacoustics
Vincent Dumoulin, Otilia Stretcu, Jenny Hamer +16
Passive acoustic monitoring (PAM) has shown great promise in helping ecologists understand the health of animal populations and ecosystems. However, extracting insights from millio…
Matching Feature Sets for Few-Shot Image Classification
Arman Afrasiyabi, Hugo Larochelle, Jean-François Lalonde +1
In image classification, it is common practice to train deep networks to extract a single feature vector per input image. Few-shot classification methods also mostly follow this tr…
Classification of Sets using Restricted Boltzmann Machines
Jérôme Louradour, Hugo Larochelle
We consider the problem of classification when inputs correspond to sets of vectors. This setting occurs in many problems such as the classification of pieces of mail containing se…
On-the-Fly Adaptation of Source Code Models using Meta-Learning
Disha Shrivastava, Hugo Larochelle, Daniel Tarlow
The ability to adapt to unseen, local contexts is an important challenge that successful models of source code must overcome. One of the most popular approaches for the adaptation…
Learning where to Attend with Deep Architectures for Image Tracking
Misha Denil, Loris Bazzani, Hugo Larochelle +1
We discuss an attentional model for simultaneous object tracking and recognition that is driven by gaze data. Motivated by theories of perception, the model consists of two interac…
Static Prediction of Runtime Errors by Learning to Execute Programs with External Resource Descriptions
David Bieber, Rishab Goel, Daniel Zheng +2
The execution behavior of a program often depends on external resources, such as program inputs or file contents, and so cannot be run in isolation. Nevertheless, software develope…
On Catastrophic Interference in Atari 2600 Games
William Fedus, Dibya Ghosh, John D. Martin +3
Model-free deep reinforcement learning is sample inefficient. One hypothesis -- speculated, but not confirmed -- is that catastrophic interference within an environment inhibits le…
Meta-Learning for Semi-Supervised Few-Shot Classification
Mengye Ren, Eleni Triantafillou, Sachin Ravi +5
In few-shot classification, we are interested in learning algorithms that train a classifier from only a handful of labeled examples. Recent progress in few-shot classification has…
On Nonparametric Guidance for Learning Autoencoder Representations
Jasper Snoek, Ryan Prescott Adams, Hugo Larochelle
Unsupervised discovery of latent representations, in addition to being useful for density modeling, visualisation and exploratory data analysis, is also increasingly important for…
Uniform Priors for Data-Efficient Transfer
Samarth Sinha, Karsten Roth, Anirudh Goyal +3
Deep Neural Networks have shown great promise on a variety of downstream applications; but their ability to adapt and generalize to new data and tasks remains a challenge. However,…
Sequential Model-Based Ensemble Optimization
Alexandre Lacoste, Hugo Larochelle, François Laviolette +1
One of the most tedious tasks in the application of machine learning is model selection, i.e. hyperparameter selection. Fortunately, recent progress has been made in the automation…
Training Restricted Boltzmann Machines on Word Observations
George E. Dahl, Ryan P. Adams, Hugo Larochelle
The restricted Boltzmann machine (RBM) is a flexible tool for modeling complex data, however there have been significant computational difficulties in using RBMs to model high-dime…
Learning to Combine Per-Example Solutions for Neural Program Synthesis
Disha Shrivastava, Hugo Larochelle, Daniel Tarlow
The goal of program synthesis from examples is to find a computer program that is consistent with a given set of input-output examples. Most learning-based approaches try to find a…
Are Few-Shot Learning Benchmarks too Simple ? Solving them without Task Supervision at Test-Time
Gabriel Huang, Hugo Larochelle, Simon Lacoste-Julien
We show that several popular few-shot learning benchmarks can be solved with varying degrees of success without using support set Labels at Test-time (LT). To this end, we introduc…
Hyperbolic Discounting and Learning over Multiple Horizons
William Fedus, Carles Gelada, Yoshua Bengio +2
Reinforcement learning (RL) typically defines a discount factor as part of the Markov Decision Process. The discount factor values future rewards by an exponential scheme that lead…
GuessWhat?! Visual object discovery through multi-modal dialogue
Harm de Vries, Florian Strub, Sarath Chandar +3
We introduce GuessWhat?!, a two-player guessing game as a testbed for research on the interplay of computer vision and dialogue systems. The goal of the game is to locate an unknow…
A RAD approach to deep mixture models
Laurent Dinh, Jascha Sohl-Dickstein, Hugo Larochelle +1
Flow based models such as Real NVP are an extremely powerful approach to density estimation. However, existing flow based models are restricted to transforming continuous densities…
Recurrent Mixture Density Network for Spatiotemporal Visual Attention
Loris Bazzani, Hugo Larochelle, Lorenzo Torresani
In many computer vision tasks, the relevant information to solve the problem at hand is mixed to irrelevant, distracting information. This has motivated researchers to design atten…
Clustering is Efficient for Approximate Maximum Inner Product Search
Alex Auvolat, Sarath Chandar, Pascal Vincent +2
Efficient Maximum Inner Product Search (MIPS) is an important task that has a wide applicability in recommendation systems and classification with a large number of classes. Soluti…
SatBird: Bird Species Distribution Modeling with Remote Sensing and Citizen Science Data
Mélisande Teng, Amna Elmustafa, Benjamin Akera +4
Biodiversity is declining at an unprecedented rate, impacting ecosystem services necessary to ensure food, water, and human health and well-being. Understanding the distribution of…
Modulating early visual processing by language
Harm de Vries, Florian Strub, Jérémie Mary +3
It is commonly assumed that language refers to high-level visual concepts while leaving low-level visual processing unaffected. This view dominates the current literature in comput…
An Autoencoder Approach to Learning Bilingual Word Representations
Sarath Chandar A P, Stanislas Lauly, Hugo Larochelle +4
Cross-language learning allows us to use training data from one language to build models for a different language. Many approaches to bilingual learning require that we have word-l…
Autotagging music with conditional restricted Boltzmann machines
Michael Mandel, Razvan Pascanu, Hugo Larochelle +1
This paper describes two applications of conditional restricted Boltzmann machines (CRBMs) to the task of autotagging music. The first consists of training a CRBM to predict tags t…
BRIDGE: Predicting Human Task Completion Time From Model Performance
Fengyuan Liu, Jay Gala, Nilaksh +3
Evaluating the real-world capabilities of AI systems requires grounding benchmark performance in human-interpretable measures of task difficulty. Existing approaches that rely on d…
Lacuna: A Research Map for Machine Learning
Martin Weiss, Miles Q. Li, Alejandro H. Artiles +4
Lacuna is a research map for machine learning that uses LLMs to turn papers and scholarly metadata into markdown summaries, concept elements, research directions, and research prop…
A Universal Representation Transformer Layer for Few-Shot Image Classification
Lu Liu, William Hamilton, Guodong Long +2
Few-shot classification aims to recognize unseen classes when presented with only a small number of samples. We consider the problem of multi-domain few-shot image classification,…
Language GANs Falling Short
Massimo Caccia, Lucas Caccia, William Fedus +3
Generating high-quality text with sufficient diversity is essential for a wide range of Natural Language Generation (NLG) tasks. Maximum-Likelihood (MLE) models trained with teache…
Disentangling the independently controllable factors of variation by interacting with the world
Valentin Thomas, Emmanuel Bengio, William Fedus +6
It has been postulated that a good representation is one that disentangles the underlying explanatory factors of variation. However, it remains an open question what kind of traini…
RNADE: The real-valued neural autoregressive density-estimator
Benigno Uria, Iain Murray, Hugo Larochelle
We introduce RNADE, a new model for joint density estimation of real-valued vectors. Our model calculates the density of a datapoint as the product of one-dimensional conditionals…
Learning Graph Structure With A Finite-State Automaton Layer
Daniel D. Johnson, Hugo Larochelle, Daniel Tarlow
Graph-based neural network models are producing strong results in a number of domains, in part because graphs provide flexibility to encode domain knowledge in the form of relation…
Using Descriptive Video Services to Create a Large Data Source for Video Annotation Research
Atousa Torabi, Christopher Pal, Hugo Larochelle +1
In this work, we introduce a dataset of video annotated with high quality natural language phrases describing the visual content in a given segment of time. Our dataset is based on…
Unlearning via Sparse Representations
Vedant Shah, Frederik Träuble, Ashish Malik +5
Machine \emph{unlearning}, which involves erasing knowledge about a \emph{forget set} from a trained model, can prove to be costly and infeasible by existing techniques. We propose…
Interpretable Multi-Modal Hate Speech Detection
Prashanth Vijayaraghavan, Hugo Larochelle, Deb Roy
With growing role of social media in shaping public opinions and beliefs across the world, there has been an increased attention to identify and counter the problem of hate speech…
HoME: a Household Multimodal Environment
Simon Brodeur, Ethan Perez, Ankesh Anand +6
We introduce HoME: a Household Multimodal Environment for artificial agents to learn from vision, audio, semantics, physics, and interaction with objects and other agents, all with…
Multiscale sequence modeling with a learned dictionary
Bart van Merriënboer, Amartya Sanyal, Hugo Larochelle +1
We propose a generalization of neural network sequence models. Instead of predicting one symbol at a time, our multi-scale model makes predictions over multiple, potentially overla…
Learned Equivariant Rendering without Transformation Supervision
Cinjon Resnick, Or Litany, Hugo Larochelle +2
We propose a self-supervised framework to learn scene representations from video that are automatically delineated into objects and background. Our method relies on moving objects…
MADE: Masked Autoencoder for Distribution Estimation
Mathieu Germain, Karol Gregor, Iain Murray +1
There has been a lot of recent interest in designing neural network models to estimate a distribution from a set of examples. We introduce a simple modification for autoencoder neu…