2. ML subfields

• Supervised learning

• Unsupervised learning

• Reinforcement learning

• None of them

• Supervised learning

• Unsupervised learning

• Reinforcement learning

• Supervised learning

• Unsupervised learning

• Reinforcement learning

• Supervised learning

• Unsupervised learning

• Reinforcement learning

the importance of each feature is determined by:

• Cost function

• Optimization

• Weights

• Labels

Reducing the error to the lowest possible value.

• Cost function

• Optimization

• Weights

• Labels

The difference between the predicted label and the actual label is determined by:

• Cost function

• Optimization

• Weights

• Labels

Feedback to the agent's actions is called:

• Exploration

• Reward

• Exploitation

• State

The random decisions that are taken by the agent are called:

• Exploration

• Reward

• Exploitation

• State