Richard G. Baraniuk · PaperMetrix

The science of deep learning

2020 · Proceedings of the National Academy of Sciences

Scientists today have completely different ideas of what machines can learn to do than we had only 10 y ago. In image processing, speech and video processing, machine vision, natural language processing, and classic two-player …

Can Neural Nets Learn the Same Model Twice? Investigating Reproducibility and Double Descent from the Decision Boundary Perspective

2022 · arXiv (Cornell University)

We discuss methods for visualizing neural network decision boundaries and decision regions. We use these visualizations to investigate issues related to reproducibility and generalization in neural network training. We observe that changes in model architecture …

A Blessing of Dimensionality in Membership Inference through Regularization

2022 · arXiv (Cornell University)

Is overparameterization a privacy liability? In this work, we study the effect that the number of parameters has on a classifier's vulnerability to membership inference attacks. We first demonstrate how the number of parameters of …

Training Dynamics of Deep Network Linear Regions

2023 · arXiv (Cornell University)

The study of Deep Network (DN) training dynamics has largely focused on the evolution of the loss function, evaluated on or around train and test set data points. In fact, many DN phenomenon were first …

Learning Transferable Features for Implicit Neural Representations

2024 · arXiv (Cornell University)

Implicit neural representations (INRs) have demonstrated success in a variety of applications, including inverse problems and neural rendering. An INR is typically trained to capture one signal of interest, resulting in learned neural features that …

MazeNet: An Accurate, Fast, and Scalable Deep Learning Solution for Steiner Minimum Trees