User profiles for Emmanuel Bengio
Emmanuel BengioMcGill University Verified email at mail.mcgill.ca Cited by 3587 |
Conditional computation in neural networks for faster models
Deep learning has become the state-of-art tool in many applications, but the evaluation and
training of deep models can be time-consuming and computationally expensive. The …
training of deep models can be time-consuming and computationally expensive. The …
[PDF][PDF] Gflownet foundations
Generative Flow Networks (GFlowNets) have been introduced as a method to sample a diverse
set of candidates in an active learning context, with a training objective that makes them …
set of candidates in an active learning context, with a training objective that makes them …
A closer look at memorization in deep networks
We examine the role of memorization in deep learning, drawing connections to capacity,
generalization, and adversarial robustness. While deep networks are capable of memorizing …
generalization, and adversarial robustness. While deep networks are capable of memorizing …
Flow network based generative models for non-iterative diverse candidate generation
This paper is about the problem of learning a stochastic policy for generating an object (like
a molecular graph) from a sequence of actions, such that the probability of generating an …
a molecular graph) from a sequence of actions, such that the probability of generating an …
Combining modality specific deep neural networks for emotion recognition in video
In this paper we present the techniques used for the University of Montréal's team submissions
to the 2013 Emotion Recognition in the Wild Challenge. The challenge is to classify the …
to the 2013 Emotion Recognition in the Wild Challenge. The challenge is to classify the …
Biological sequence design with gflownets
Abstract Design of de novo biological sequences with desired properties, like protein and
DNA sequences, often involves an active loop with several rounds of molecule ideation and …
DNA sequences, often involves an active loop with several rounds of molecule ideation and …
Towards understanding and improving gflownet training
Generative flow networks (GFlowNets) are a family of algorithms that learn a generative policy
to sample discrete objects $ x $ with non-negative reward $ R (x) $. Learning objectives …
to sample discrete objects $ x $ with non-negative reward $ R (x) $. Learning objectives …
Trajectory balance: Improved credit assignment in GFlowNets
Generative flow networks (GFlowNets) are a method for learning a stochastic policy for
generating compositional objects, such as graphs or strings, from a given unnormalized density …
generating compositional objects, such as graphs or strings, from a given unnormalized density …
Learning GFlowNets from partial episodes for improved convergence and stability
…, M Korablyov, E Bengio… - International …, 2023 - proceedings.mlr.press
Generative flow networks (GFlowNets) are a family of algorithms for training a sequential
sampler of discrete objects under an unnormalized target density and have been successfully …
sampler of discrete objects under an unnormalized target density and have been successfully …
Multi-objective gflownets
We study the problem of generating diverse candidates in the context of Multi-Objective
Optimization. In many applications of machine learning such as drug discovery and material …
Optimization. In many applications of machine learning such as drug discovery and material …