4: Can Neural Nets Learn the Same Model Twice?

<p>Todays paper: Can Neural Nets Learn the Same Model Twice? Investigating Reproducibility<br/>and Double Descent from the Decision Boundary Perspective (https://arxiv.org/pdf/2203.08124.pdf)<br/><br/>Summary:<br/>A discussion of reproducibility and double descent through visualizations of decision boundaries.<br/><br/>Highlights of the discussion:</p><ul><li>Relationship between model performance and reproducibility</li><li>Which models are robust and reproducible</li><li>How they calculate the various scores</li></ul><p><br/><br/></p>