Picture for George Dahl

George Dahl

Training neural networks faster with minimal tuning using pre-computed lists of hyperparameters for NAdamW

Add code
Mar 06, 2025
Viaarxiv icon

A Loss Curvature Perspective on Training Instability in Deep Learning

Add code
Oct 08, 2021
Figure 1 for A Loss Curvature Perspective on Training Instability in Deep Learning
Figure 2 for A Loss Curvature Perspective on Training Instability in Deep Learning
Figure 3 for A Loss Curvature Perspective on Training Instability in Deep Learning
Figure 4 for A Loss Curvature Perspective on Training Instability in Deep Learning
Viaarxiv icon

Relational inductive biases, deep learning, and graph networks

Add code
Oct 17, 2018
Figure 1 for Relational inductive biases, deep learning, and graph networks
Figure 2 for Relational inductive biases, deep learning, and graph networks
Figure 3 for Relational inductive biases, deep learning, and graph networks
Figure 4 for Relational inductive biases, deep learning, and graph networks
Viaarxiv icon

Peptide-Spectra Matching from Weak Supervision

Add code
Aug 22, 2018
Figure 1 for Peptide-Spectra Matching from Weak Supervision
Figure 2 for Peptide-Spectra Matching from Weak Supervision
Figure 3 for Peptide-Spectra Matching from Weak Supervision
Figure 4 for Peptide-Spectra Matching from Weak Supervision
Viaarxiv icon