The WSD Learning Rate Schedule
·52 words·1 min
Blog
Flossing with Forever Chemicals? Switch to Silk!
·20 words·1 min
Power of Search Default
·94 words·1 min
Tricky Validation Accuracy Plot
·31 words·1 min
Code in Papers
·48 words·1 min
DeepMind's Chess Model
·344 words·2 mins
Solving Chicken-Egg Dilemma
·20 words·1 min
Robots: Just Tools in AI's Toolbox?
·24 words·1 min
Quantization Eats the Long Tail
·40 words·1 min
AdamW Who? A New Optimizer Steals the Show
·454 words·3 mins