引導式測驗 · 中等 等級
持續學習與災難性遺忘測驗
回顧災難性遺忘、穩定性可塑性、EWC、重播、任務族和持續學習限制。檢查範圍和假設。
問題 1 的 8
什麼是「災難性遺忘」?
預覽每個問題8 問題
當您參加測驗時,就會出現答案和解釋。
- 什麼是「災難性遺忘」?
- 當學習新任務會大幅降低先前學習任務的表現時
- 當模型記憶體不足並崩潰時
- 當訓練資料被意外刪除時
- 當模型拒絕做出預測時
- 持續學習的核心權衡通常被稱為:
- 偏差-方差權衡
- 穩定性-可塑性困境
- 速度與精度的權衡
- 探索-利用權衡
- 彈性權重合併 (EWC) 有什麼作用?
- 刪除不重要的神經元
- 新任務的學習率加倍
- 懲罰對之前學習的任務很重要的權重變化
- 永久儲存過去的每個訓練範例
- 基於重播的方法如何對抗遺忘?
- 透過永久凍結整個網絡
- 透過使用更大的學習率
- 透過刪除損失函數
- 透過將儲存或產生的舊範例交錯到新訓練中
- 梯度情景記憶(GEM)如何在學習新任務時限制梯度更新?
- It projects the gradient so its first-order approximation does not increase loss on stored prior-task examples
- It replaces all prior-task data with new examples
- It freezes every parameter for all future tasks
- It increases weights that were unimportant to earlier tasks
- 為什麼對新任務進行天真的微調會導致遺忘?
- GPU 過熱並損壞內存
- 梯度下降將共享權重移向新任務,而沒有保留舊任務的限制
- 新任務總是有更多數據
- 模型有意刪除舊權重
- How does iCaRL classify a test example after learning multiple classes?
- By retrieving the single closest word in a text corpus
- By selecting the class with the largest Fisher information
- By comparing its feature vector with per-class means computed from stored exemplars
- By replaying every training image at inference
- Why is evaluating continual learning more than measuring final accuracy on the newest task?
- New-task accuracy is the only relevant measure
- Old tasks are removed from the evaluation
- The model cannot be tested on multiple tasks
- A method must also measure retention on prior tasks and its ability to learn new ones