Machine Learning and having it deep and structured (MLDS) at NTU 2018 Spring.

This course has four homeworks, group by group. The four homeworks are as follows:

1. Deep Learning Theory
2. Sequence-to-sequence Model
3. Deep Generative Model
4. Deep Reinforcement Learning

Browse this course website for more details.

1. Deep Learning Theory
   • Deep vs Shallow
   • Optimization
   • Generalization
2. Sequence-to-sequence Model
   • Video caption generation
   • Chat-bot
3. Deep Generative Model
   • Image Generation
   • Text-to-Image Generation
   • Style Transfer
4. Deep Reinforcement Learning
   • Policy Gradient
   • Deep Q Learning
   • Actor-Critic

• Report.pdf

• README

• README

• README

• BLEU@1 = 0.7204
• README
• hw2_1/report.pdf

• Perplexity = 11.83, Correlation Score = 0.53626
• README
• hw2_2/report.pdf

• report.pdf

• README
• Image Generation: 100% (25/25) Pass Baseline

./gan-baseline/baseline_result_gan.png

• README
• Text-to-Image Generation: 100% (25/25) Pass Baseline

Testing Tags	./gan-baseline/baseline_result_cgan.png
blue hair blue eyes blue hair green eyes blue hair red eyes green hair blue eyes green hair red eyes

• README

• report.pdf

• README
• Policy Gradient: Mean Rewards in 30 Episodes = 16.466666666666665

• README
• Deep Q Learning: Mean Rewards in 100 Episodes = 73.16

• README