引導式測驗 · 中等 等級
神經架構搜尋測驗
查看 NAS 搜尋空間、演算法、早期搜尋成本、DARTS 鬆弛、權重共享和評估注意事項。檢查假設和範圍。
問題 1 的 8
神經架構搜尋自動化什麼?
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。
- 神經架構搜尋自動化什麼?
- 神經網路結構的設計
- 標記訓練數據
- 冷卻 GPU 伺服器
- 為模型撰寫文檔
- 哪三個元件定義了 NAS 方法?
- 資料集、優化器和 dropout
- 搜尋空間、搜尋策略和效能估計
- 編碼器、解碼器和注意力
- 訓練、驗證和測試集
- What accelerator scale did the original reinforcement-learning NAS paper report for its large search?
- One GPU for every NAS method
- A fixed cost of exactly 1,000 GPU-days for every search
- An experiment using 800 GPUs in that study
- No accelerator use during architecture search
- DARTS 使用什麼關鍵技巧來提高搜尋效率?
- 它在單一範例上進行訓練
- 它刪除所有隱藏層
- 它僅使用隨機搜索
- 它將離散的架構選擇放鬆為可透過梯度優化的連續架構
- 權重共享 NAS 中的「超級網」是什麼?
- 一個包含所有候選架構的超參數化網絡,其權重是共享的
- 具有數十億參數的網絡
- 僅在超級電腦上運行的網絡
- 模型的備份副本
- What did the HURRICANE hardware-aware NAS study evaluate?
- One architecture that is guaranteed optimal on every device
- Tailored architectures for three hardware types under matched latency constraints
- A language model trained without any hardware measurements
- A method that removes latency from architecture evaluation
- What is one limitation of weight-sharing NAS supernets?
- They remove all architecture choices
- They guarantee the globally best architecture
- The shared weights can bias architecture rankings relative to training each candidate independently
- They do not use neural networks
- What does a NAS evaluation need to report for a fair comparison?
- Only the best test score
- The GPU brand alone
- The model name without settings
- Search space, compute budget, validation protocol, and final retraining setup