跳到主要內容區塊
:::
A- A A+

博士後演講公告

:::

Confidence Training with Logically-lucid Pattern

  • 2024-05-15 (Wed.), 14:00 PM
  • 統計所B1演講廳;茶 會:13:40。
  • 實體與線上視訊同步進行。
  • Dr. Yu-Cheng Li ( 李育誠 博士 )
  • 中央研究院統計科學研究所資深協同研究學者

Abstract

Wrong prediction is bad. For users, having high confidence in a wrong prediction is even worse. Since even the best-trained class-label predictor will have some chance of making mistakes, users, especially in some AI application areas, such as personalized medicine, may want to tell high-quality predictions from low-quality ones. In convolutional neural networks (CNN), confidence in a prediction is associated with the softmax output layer, which gives a probability distribution on the class labels. But even a prediction with 95% probability concentrated on one class may still turn out wrong many times more often than the anticipated rate of 5%. Here, we take a different approach, termed post-prediction confidence training (PPCT), to guide users on how to discern high-quality predictions from low-quality ones.  An enhancement to CNN configuration is required during network training. We propose a blueprint by coupling each logit node (T channel) in the layer feeding to softmax with an additional node (C channel) and using maxout to link the pair to the softmax layer. The C channel is introduced to counter the T channel as a contrastive feature against the feature of the target class. A high-quality prediction must follow a logically-lucid pattern between T and C for every class. Successful implementations of our methods on popular image datasets are reported.

線上視訊請點選連結

 

附件下載

1130515_Dr. Yu-Cheng Li.pdf
最後更新日期:2024-05-08 13:59
回頁首