An artificial intelligence (AI) model can be viewed as a function that maps inputs to outputs in high-dimensional spaces. Once designed and well trained, the AI model is applied for inference. However, even optimized AI models can produce inference errors due to aleatoric and epistemic uncertainties. Interestingly, we observed that when inferring multiple samples based on invariant transformations of an input, inference errors can show partial independences due to epistemic uncertainty. Leveraging this insight, we propose a "resampling" based inferencing that applies to a trained AI model with multiple transformed versions of an input, and aggregates inference outputs to a more accurate result. This approach has the potential to improve inference accuracy and offers a strategy for balancing model size and performance.

翻译：人工智能模型可视为在高维空间中实现输入到输出映射的函数。模型一旦设计完成并经过充分训练，即可用于推理。然而，即使经过优化的AI模型，由于偶然不确定性和认知不确定性的存在，仍可能产生推理误差。有趣的是，我们观察到：当基于输入的不变变换推断多个样本时，推理误差会因认知不确定性而表现出部分独立性。基于这一发现，我们提出一种基于“重采样”的推理方法：对训练完成的AI模型输入经过多重变换的版本，通过聚合推理输出来获得更准确的结果。该方法有望提升推理精度，并为平衡模型规模与性能提供新策略。