q-Neurons: stochastic Jackson-derivative activations consistently beat standard ones
FrnkNlsn · x · 2026-09-23
A paper by Frank Nielsen and Ke Sun (IEEE TNNLS 2020) introduces q-neurons, neurons whose activations are based on Jackson's q-derivatives with stochastic parameter q. The authors show the generalization is scalable and easy to implement, with experiments demonstrating consistently improved training and test losses over state-of-the-art standard activation functions.
More from Research
- Researchers lament: no good RL environment sets exist that allow diffing behaviors across training runs — 1a3orn · 2026-09-23
- New PNAS paper: human learning is an understudied lever for boosting human–AI synergy — iyadrahwan · 2026-09-23
- MotionJEPA: Oxford-led team fixes JEPA world models' bias toward slow, simple features — randall_balestr · 2026-09-23
- MIT researchers compile a trained neural network into DNA inside mammalian cells — NikoMcCarty · 2026-09-23
- Agent design rule: verifiers may give feedback but never promote candidates — blaizedsouza · 2026-09-23
- OpenAI said to launch journal with multi-agent AI reviews, threatening ML conferences — kfountou · 2026-09-23