Kvíz spojený s průvodcem · Snadno úroveň
Kvíz Jak se AI učí
Zkontrolujte, jak rozumíte učení pod dohledem, bez dozoru a posilování, plus přemontování, testovací sady a to, co vlastně měří ztráta modelu.
Otázka 1 z 8
Co zahrnují tréninková data v řízeném učení?
Náhled každé otázky8 otázky
Odpovědi a vysvětlení se zobrazují, jak budete v kvízu.
- Co zahrnují tréninková data v řízeném učení?
- Only raw examples with no answers attached
- Rules written by programmers for every possible situation
- Inputs paired with target outputs, called labels
- Rewards and penalties from a game environment
- Příkladem jakého typu učení je seskupování zákazníků podle podobných nákupních zvyklostí bez předem definovaných kategorií?
- Učení bez dozoru
- Rule-based programming
- Učení pod dohledem
- Posílení učení
- Jak se posilovací výukový agent, jako ten, který se učí hrát videohru, zlepšuje?
- By trying actions and learning from rewards or penalties
- By memorizing the game's source code
- By copying labeled examples showing the correct move each turn
- By sorting past games into clusters without feedback
- A model performs well on its training examples but poorly on comparable held-out examples. Which pattern does this show?
- Podvybavení
- Přetahování
- Data leakage
- Dobrá generalizace
- Why keep a test set separate from fitting the model and choosing its settings?
- To estimate performance on examples not used for those development choices
- To tune hyperparameters by repeatedly checking the final evaluation set
- To add held-out examples to training after the choices are final
- To check whether training predictions match their training labels
- In the guide’s supervised training loop, what does the loss measure?
- How much electricity the training run uses
- How long the model takes to give an answer
- How many examples were deleted from the training dataset
- The numerical difference between predictions and target values
- A text model learns to predict the next token from the preceding context. Which learning setup does the guide describe?
- Supervised learning with separately supplied labels
- Unsupervised clustering of the text
- Self-supervised training that creates a prediction task from the text
- Reinforcement learning from rewards for each token
- A model changes its answer after seeing an example in a prompt. What can be concluded about its learned weights?
- They must have permanently changed
- The prompt became part of every user’s training data
- The model cannot use examples without retraining
- A changed response does not by itself show a weight update