Newest papers

Stochastic Nonlinearities Improve Uncertainty Estimation

Mohammad Sarhangzadeh, Amirreza M. Shebly, Doruk Oner · 2026 · arXiv

DOI: 10.48550/arXiv.2610.29875 · open-access PDF

Russian

Многие методы оценки неопределенности получают предсказуемое разнообразие через механизмы, которые могут подавлять промежуточные функции, нарушать вход или требуют существенных дополнительных вычислений.Стохастические функции активации, где сетевые единицы случайно выбирают между несколькими нелинейностями во время перехода вперед, ранее использовались для улучшения поведения оптимизации, смягчения ограничений фиксированных активаций ReLU и увеличения выхода

Machine translation (Meta M2M100); the English original follows.

Abstract

Reliable uncertainty estimation is important across visual recognition tasks, providing information about the confidence and reliability of model predictions. Many uncertainty estimation methods obtain predictive diversity through mechanisms that can suppress intermediate features, perturb the input, or require substantial additional computation. Stochastic activation functions, where network units randomly select between multiple nonlinearities during a forward pass, have previously been used to improve optimization behavior, mitigate limitations of fixed ReLU activations, and increase output

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.29875, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange