Publications

. . An End-to-End Deep Embedding Framework For Malware Detection and An Interpretable Plug-in for Convolutional Neural Network, 2017.

Preprint

. . A Classification model for Diverse and Noisy Labelers, 2017.

Preprint PDF

Projects

All Deep Learning Kaggle Other

NIPS2017 Adversarial Example Defense

Create an image classifier that is robust to adversarial attacks (40⁄107)

Facebook: Predicting Check Ins

Identify the correct place for check ins (top 6%, 72⁄1212)

Expedia Hotel Rec.

Predict which hotel the customer will book (top 7%,121⁄1974)

Recent Posts

25 min read
Abstract: Generative adversarial network (GAN) has shown siginificant imporvments of learning latent representation of high-dimensional continuous data such as images and videos. Many amazing applications such as video synthesis and image translation are based on the capability of GAN. Unfortunately, applying GAN to discrete input remain a challenging problem. One of reasons is the discrete nature of data prevent the discriminator from providing useful gradient information for learning. In this post, I will foucus on some recent techniques to address this difficulty in the text generation and the evaluation

CONTINUE READING

Contact