yao-jason/MLDS2018SPRING

Course materials covering four major deep learning domains: seq2seq models for video captioning and dialogue, generative models (GANs for conditional image synthesis and style transfer), and reinforcement learning algorithms (policy gradient, DQN, actor-critic). Implementations include theoretical foundations on optimization and generalization, with practical applications spanning computer vision and natural language processing tasks.

146 stars. No commits in the last 6 months.