引導式測驗 · 中等 等級
週期性學習率測驗
檢查三角學習率循環、範圍測試、動量行為以及重複循環和單循環訓練之間的差異。
問題 1 的 8
週期性學習率挑戰了什麼核心假設?
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。
- 週期性學習率挑戰了什麼核心假設?
- 學習率只會在訓練期間降低
- 批量大小必須保持不變
- 該模型需要 GPU
- 該數據必須被打亂
- What did Smith report for cyclical learning rates on tested classification tasks?
- They always lowered training loss to zero
- They improved accuracy versus fixed rates, often in fewer iterations
- They removed the need for validation data
- They guaranteed escape from every sharp minimum
- 「LR 範圍測試」有什麼作用?
- 測量 GPU 記憶體使用量
- 計算模型參數的數量
- 向上調整學習率,同時觀察損失以選擇適當的範圍
- 使用分佈外資料測試模型
- 在單週期策略中,動量相對於學習率通常如何表現?
- 動量始終保持固定
- 動量始終設定為零
- 動量與速率完全同步增加
- 動量反向移動-利率低時動量高,利率高時動量低
- During a triangular cyclical learning-rate cycle, how does the rate move between its bounds?
- It rises from the base rate to the maximum, then falls back toward the base
- It only decreases from the first step
- It stays fixed at the maximum
- It jumps randomly at every minibatch
- 誰引入了循環學習率和 LR 範圍測試?
- 傑弗裡·辛頓
- 萊斯利史密斯
- 嚴樂存
- 安德烈·卡帕蒂
- What sets the duration of a cyclical learning-rate cycle?
- 模型層數
- 詞彙量大小
- A chosen number of training iterations for the up-and-down pattern
- The number of optimizer parameters
- What distinguishes the one-cycle policy from repeating several triangular cycles?
- It keeps the learning rate constant throughout
- It removes the optimizer’s momentum
- It measures the learning rate only once
- It uses one long learning-rate cycle for the training run