Infinite width (finite depth) neural networks benefit from multi-task learning unlike shallow Gaussian Processes -- an exact quantitative macroscopic characterization

Add code
Jan 05, 2022
Figure 1 for Infinite width (finite depth) neural networks benefit from multi-task learning unlike shallow Gaussian Processes -- an exact quantitative macroscopic characterization

Share this with someone who'll enjoy it:

View paper onarxiv icon

Share this with someone who'll enjoy it: