RNN can save context information.

Markov chain is a commonly used algorithm for natural language. What are the properties of Markov chain? (Multiple choice)

Reinforcement learning is different from supervised learning in connectionist learning, mainly in terms of teacher signals. In reinforcement learning, the reinforcement signal provided by the environment is an evaluation of the quality of the action (usually a scalar signal), rather than telling the reinforcement learning system how to generate the correct action.

When using a convolutional neural network, it is usually sufficient to directly input the original image without artificial preprocessing and feature extraction.

What are the models used in traditional speech recognition? (Multiple choice)