গাইড লিঙ্ক ক্যুইজ · কঠিন স্তর
Gumbel-Softmax এবং Reparameterization কুইজ
শ্রেণীবদ্ধ নমুনা পরীক্ষা, পার্থক্যযোগ্য শিথিলকরণ, গাম্বেল শব্দ, তাপমাত্রা, কঠিন পছন্দ এবং নরম আউটপুটগুলির সীমা।
প্রশ্ন 1 এর 8
Why is a categorical sample difficult to train through with ordinary backpropagation?
প্রতিটি প্রশ্নের পূর্বরূপ দেখুন8 প্রশ্ন
আপনি কুইজ নেওয়ার সাথে সাথে উত্তর এবং ব্যাখ্যাগুলি উপস্থিত হয়।
- Why is a categorical sample difficult to train through with ordinary backpropagation?
- Categorical distributions have no probabilities
- The discrete choice is a non-differentiable operation
- Sampling removes the input tensor
- All categories have identical logits
- What does the reparameterization trick aim to do?
- Remove all randomness from training
- Replace gradients with labels
- Make categorical outputs continuous at evaluation time
- Express randomness through an external noise variable while keeping a differentiable path
- How does Gumbel-Softmax approximate a categorical choice?
- Use a hard class label as a gradient
- Normalize the input pixels
- Add Gumbel noise to logits and apply a temperature-controlled softmax
- Average logits across unrelated examples
- What happens to the distribution as temperature becomes large?
- It becomes smoother across categories
- It becomes an exact one-hot sample
- The logits are discarded
- It becomes independent of the Gumbel noise
- What happens as temperature approaches zero?
- The output becomes uniform
- The noise becomes a label
- The operation stops depending on logits
- The output becomes sharper and closer to a discrete one-hot choice
- What does the Gumbel-Max trick produce?
- A differentiable mean over all categories
- An exact categorical sample by adding independent Gumbel noise to logits and taking argmax
- A uniform distribution regardless of logits
- A gradient estimate from labels
- Why is Gumbel-Softmax useful in a neural model?
- It provides a differentiable relaxation for discrete choices during training
- It makes every model deterministic
- এটি সমস্ত লুকানো স্তর প্রতিস্থাপন করে
- It guarantees the learned category is correct
- What should be remembered about a low-temperature soft sample?
- It is always a ground-truth label
- It no longer depends on probabilities
- It is a near-discrete relaxation, not necessarily identical to a hard argmax in every training setup
- It guarantees zero estimation bias