125 citations · 238 across the 12 of their papers we have counts for
7 papers · 1 filter
Perch 2.0 transfers 'whale' to underwater tasks
Andrea Burns, Lauren Harrell, Bart van Merriënboer +3
Perch 2.0 is a supervised bioacoustics foundation model pretrained on 14,597 species, including birds, mammals, amphibians, and insects, and has state-of-the-art performance on mul…
BIRB: A Generalization Benchmark for Information Retrieval in Bioacoustics
Jenny Hamer, Eleni Triantafillou, Bart van Merriënboer +4
The ability for a machine learning model to cope with differences in training and deployment conditions--e.g. in the presence of distribution shift or the generalization to new cla…
GradMax: Growing Neural Networks using Gradient Information
Utku Evci, Bart van Merriënboer, Thomas Unterthiner +2
The architecture and the parameters of neural networks are often optimized independently, which requires costly retraining of the parameters whenever the architecture is modified.…
On the interplay between noise and curvature and its effect on optimization and generalization
Valentin Thomas, Fabian Pedregosa, Bart van Merriënboer +3
The speed at which one can minimize an expected loss using stochastic methods depends on two properties: the curvature of the loss and the variance of the gradients. While most pre…
Automatic differentiation in ML: Where we are and where we should be going
Bart van Merriënboer, Olivier Breuleux, Arnaud Bergeron +1
We review the current state of automatic differentiation (AD) for array programming in machine learning (ML), including the different approaches such as operator overloading (OO) a…
Tangent: Automatic differentiation using source-code transformation for dynamically typed array programming
Bart van Merriënboer, Dan Moldovan, Alexander B Wiltschko
The need to efficiently calculate first- and higher-order derivatives of increasingly complex models expressed in Python has stressed or exceeded the capabilities of available tool…
Blocks and Fuel: Frameworks for deep learning
Bart van Merriënboer, Dzmitry Bahdanau, Vincent Dumoulin +4
We introduce two Python frameworks to train neural networks on large datasets: Blocks and Fuel. Blocks is based on Theano, a linear algebra compiler with CUDA-support. It facilitat…