• Publications
  • Influence
Weight Uncertainty in Neural Networks
TLDR
This work introduces a new, efficient, principled and backpropagation-compatible algorithm for learning a probability distribution on the weights of a neural network, called Bayes by Backprop, and shows how the learnt uncertainty in the weights can be used to improve generalisation in non-linear regression problems. Expand
Weight Uncertainty in Neural Network
TLDR
This work introduces a new, efficient, principled and backpropagation-compatible algorithm for learning a probability distribution on the weights of a neural network, called Bayes by Backprop, and shows how the learnt uncertainty in the weights can be used to improve generalisation in non-linear regression problems. Expand
On optimality of kernels for approximate Bayesian computation using sequential Monte Carlo
TLDR
This paper discusses how to construct the perturbation kernels that are required in ABC SMC approaches, in order to construct a sequence of distributions that start out from a suitably defined prior and converge towards the unknown posterior. Expand
Adaptive methods for sequential importance sampling with application to state space models
TLDR
New adaptive proposal strategies for sequential Monte Carlo algorithms—also known as particle filters—relying on criteria evaluating the quality of the proposed particles are discussed, establishing an empirical estimate of linear complexity of the Kullback-Leibler divergence between the involved distributions. Expand
Deep Learning and Data Labeling for Medical Applications
TLDR
The proposed K-support spatial pooling strategy in deep CNNs combines the popularly applied mean and max pooling methods, and then avoids awfully emphasizing of the maximum activation but preferring a group of activations in a supported region. Expand
AI for social good: unlocking the opportunity for positive impact
TLDR
This work provides a set of guidelines for establishing successful long-term collaborations between AI researchers and application-domain experts, relate them to existing AI4SG projects and identify key opportunities for future AI applications targeted towards social good. Expand
Adaptive sequential Monte Carlo by means of mixture of experts
TLDR
A novel algorithm adaptively approximating the so-called optimal proposal kernel by a mixture of integrated curved exponential distributions with logistic weights, broad enough to be used in the presence of multi-modality or strongly skewed distributions. Expand
HighRes-net: Recursive Fusion for Multi-Frame Super-Resolution of Satellite Imagery
TLDR
HighRes-net is presented, the first deep learning approach to MFSR that learns its sub-tasks in an end-to-end fashion, and shows that by learning deep representations of multiple views, it can super-resolve low-resolution signals and enhance Earth Observation data at scale. Expand
A comparative study of Monte-Carlo methods for multitarget tracking
TLDR
A comparative study of several Monte Carlo methods in terms of estimation quality and complexity of multitarget tracking problem is presented. Expand
Méthodes de Monte Carlo séquentielles adaptatives
...
1
2
3
...