Bayesian Attention Modules Xinjie Fan

Aug-16-2025, 03:39:29 GMT–Neural Information Processing Systems

Most current models use deterministic attention modules due to their simplicity and ease of optimization. Stochastic counterparts, on the other hand, are less popular despite their potential benefits.

arxiv preprint arxiv, attention module, attention weight, (13 more...)

Neural Information Processing Systems

Aug-16-2025, 03:39:29 GMT

Conferences PDF

Country:
- Europe > Spain
  - Catalonia > Barcelona Province > Barcelona (0.04)
- North America
  - Canada (0.04)
  - United States
    - Michigan > Washtenaw County
      - Ann Arbor (0.04)
    - Texas > Travis County
      - Austin (0.04)

Genre:
- Research Report > New Finding (0.46)

Technology:
- Information Technology > Artificial Intelligence
  - Machine Learning
    - Learning Graphical Models > Directed Networks
      - Bayesian Learning (0.93)
    - Neural Networks > Deep Learning (1.00)
  - Natural Language > Machine Translation (0.70)
  - Representation & Reasoning > Uncertainty
    - Bayesian Inference (0.93)
  - Vision (0.70)