4 papers
When Bias Meets Trainability: Connecting Theories of Initialization
Alberto Bassi, Marco Baity-Jesi, Aurelien Lucchi +2
The statistical properties of deep neural networks (DNNs) at initialization play an important role to comprehend their trainability and the intrinsic architectural biases they poss…
Where You Place the Norm Matters: From Prejudiced to Neutral Initializations
Emanuele Francazi, Francesco Pinto, Aurelien Lucchi +1
Normalization layers were introduced to stabilize and accelerate training, yet their influence is critical already at initialization, where they shape signal propagation and output…
Producing Plankton Classifiers that are Robust to Dataset Shift
Cheng Chen, Sreenath Kyathanahally, Marta Reyes +6
Modern plankton high-throughput monitoring relies on deep learning classifiers for species recognition in water ecosystems. Despite satisfactory nominal performances, a significant…
Initial Guessing Bias: How Untrained Networks Favor Some Classes
Emanuele Francazi, Aurelien Lucchi, Marco Baity-Jesi
Understanding and controlling biasing effects in neural networks is crucial for ensuring accurate and fair model performance. In the context of classification problems, we provide…