引導式測驗 · 中等 等級
變分自動編碼器測驗
回顧 VAE 分佈、重新參數化、KL 正規化、ELBO 訓練、採樣和潛在擴散使用。檢查證據和範圍。
問題 1 的 8
對於給定的輸入,VAE 中的編碼器輸出什麼?
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。
- 對於給定的輸入,VAE 中的編碼器輸出什麼?
- 機率分佈的參數,例如平均值和方差
- 潛在空間中的單一固定點
- 一個類別標籤
- 輸入的重構副本
- 重新參數化技巧的目的是什麼?
- 使解碼器更大
- 允許梯度流過隨機採樣步驟
- 消除對解碼器的需要
- 進一步壓縮潛在空間
- In the standard Gaussian VAE formulation, what does the KL term encourage?
- The decoder to predict future input tokens
- The encoder to remove all randomness
- The approximate posterior to stay close to the chosen prior, commonly a standard normal
- Every latent variable to have the same observed value
- VAE 在訓練期間最大化的目標函數稱為:
- 交叉熵上限
- 對抗性損失
- 均方餘裕
- 證據下限 (ELBO)
- In a Gaussian VAE, what enables generation of a new sample?
- Sample a latent from the prior and decode it with the learned decoder
- Copy a training image directly without a model
- Run the encoder backward with no latent sampling
- Choose a random class label without decoding
- 在穩定擴散這樣的潛在擴散模型中,VAE 發揮什麼作用?
- 它標記訓練圖像
- 它將影像壓縮到擴散運行的潛在空間,然後解碼回像素
- 它取代了文字編碼器
- 它安排噪音水平
- In variational inference, what does the ELBO provide for the marginal log likelihood log p(x)?
- An exact value of log p(x) for every model
- A guarantee that each generated sample is realistic
- A tractable lower bound that can be maximized instead of directly maximizing log p(x)
- A posterior distribution that requires no inference model
- What distribution does a VAE decoder model given a latent vector?
- The encoder’s approximate posterior q(z|x)
- The training set’s class-frequency histogram only
- The optimizer’s learning-rate schedule
- The likelihood of an observation conditioned on that latent, p(x|z)