Search Results for author:
Found 9 papers, 0 papers with code
A Deep Neural Networks ensemble workflow from hyperparameter search to inference leveraging GPU clusters
Finally, we propose a novel algorithm to optimize the inference of the DNNs ensemble in a GPU cluster based on allocation optimization.
Weakly Supervised Faster-RCNN+FPN to classify animals in camera trap images
First, it automatically performs the weakly-supervised bounding box annotation using the motion from multiple frames.
Distributed Ensembles of Reinforcement Learning Agents for Electricity Control
Deep Reinforcement Learning (or just "RL") is gaining popularity for industrial and research applications.
An efficient and flexible inference system for serving heterogeneous ensembles of deep neural networks
Experiments show the flexibility and efficiency under extreme scenarios: It successes to serve an ensemble of 12 heavy DNNs into 4 GPUs and at the opposite, one single DNN multi-threaded into 16 GPUs.
AutoML to generate ensembles of deep neural networks
Automated Machine Learning with ensembling seeks to automatically build ensembles of Deep Neural Networks (DNNs) to achieve qualitative predictions.
Recycling sub-optimial Hyperparameter Optimization models to generate efficient Ensemble Deep Learning
Due to the lack of consensus to design a successful deep learning ensemble, we introduce Hyperband-Dijkstra, a new workflow that automatically explores neural network designs with Hyperband and efficiently combines them with Dijkstra's algorithm.
Ranking Viscous Finger Simulations to an Acquired Ground Truth with Topology-aware Matchings
Different metrics, based on optimal transport, for comparing time-varying persistence diagrams in this specific applicative case are introduced.
Lifted Wasserstein Matcher for Fast and Robust Topology Tracking
First, we revisit the seminal assignment algorithm by Kuhn and Munkres which we specifically adapt to the problem of matching persistence diagrams in an efficient way.
Topologically Controlled Lossy Compression
However, in many scenarios it is desirable to control in a similar way the preservation of higher-level notions, such as topological features , in order to provide guarantees on the outcome of post-hoc data analyses.
