An algorithmic framework for the optimization of deep neural networks architectures and hyperparameters

no code implementations • 27 Feb 2023 • Julie Keisler, El-Ghazali Talbi, Sandra Claudel, Gilles Cabriel

Based on this search space we propose neighbourhood and evolution search operators to optimize both the architecture and hyper-parameters of our networks.

Time Series Time Series Prediction

Transfer Learning for Linear Regression: a Statistical Test of Gain

no code implementations • 18 Feb 2021 • David Obst, Badih Ghattas, Jairo Cugliari, Georges Oppenheim, Sandra Claudel, Yannig Goude

Transfer learning, also referred as knowledge transfer, aims at reusing knowledge from a source dataset to a similar target one.

regression Transfer Learning

Textual Data for Time Series Forecasting

no code implementations • 25 Oct 2019 • David Obst, Badih Ghattas, Sandra Claudel, Jairo Cugliari, Yannig Goude, Georges Oppenheim

While ubiquitous, textual sources of information such as company reports, social media posts, etc.

Time Series Time Series Forecasting +1