The 5.5 Cliff: The Bug in Every Softmax That Silently Zeroes Your Model's Best Gradient
Every model you have ever trained runs through the same two functions: softmax turns raw scores into probabilities, and cross-entropy scores how wrong those probabilities were. On October 22, 2026, three Google DeepMind researchers — Jonathan T. Barron, Dan Gnanapragasam, and Michael Tschannen — po…
Read the full story at DEV Community — Machine Learning ↗
Timeline · 1 report
- 2026-10-25 15:55 · DEV Community — Machine Learning
The 5.5 Cliff: The Bug in Every Softmax That Silently Zeroes Your Model's Best Gradient