Logo image
A Self-Improving GAN for Decoding Variational RNNs
Thesis

A Self-Improving GAN for Decoding Variational RNNs

Chuang, Chi-Chun
Masters, 國立清華大學, 資訊工程學系所
2017

Abstract

機器學習 人工智慧 神經網路 生成模型 Machine Learning Artificial Intelligence Neural Networks Generative Adversarial Networks
Current RNN decoding methods usually focus on how to generate high quality sequences, but they ignore the importance of variety on the collection of outputs. Our work introduces a new model architecture to let RNN generate high quality and variety sequences. We extend the Generative Adversarial Networks and propose Strong-Weak Collaborative GAN. We separate the generator into two part, strong and weak, to cooperatively generate a sequence to cheat discriminator. To further improve our model, we make our model to improve itself, namely Self-improving Collaborative GAN (SIC-GAN). SIC-GAN can generate not only high quality and variety sequences, but also to produce “creative” outputs. Experimental result shows that our model can generate higher quality and more diverse results than all the baseline.

Metrics

1 Record Views

Details

Logo image