Assignment

Assignment 1 - Sequence Labeling

Speech is composed of phomenes. This task is to predict the associated phone sequences given the acoustic signal.

Read assignment page Read assignment slides

Assignment 2 - Video Captioning

Describe the videos based on content.
This task is to generate the description for the given video.

Read assignment page Read assignment slides

Assignment 3 - Game Playing

Game playing is an interaction between a user and an environment. Reinforcement learning can learn the agent's action for plying the games.

Task 1: implement a value-based approach for the agent to play the game.
Task 2: implement a policy-based approach for the agent to play the game.

Read assignment page Read assignment slides

Assignment 4 - Comics Generation

Conditional image generation is to automatically generate natural images based on the given constraints.

Read assignment page Read assignment slides

Teaching Assistants (TBA)