no code implementations • 2 Oct 2019 • Dakila Ledesma, Yu Liang, Dalei Wu
This paper proposed a hierarchical visible autoencoder in the adaptive phantom limbs generation according to the kinetic behavior of functional body-parts, which are measured by heterogeneous kinetic sensors.
no code implementations • ICLR 2018 • Dalei Wu, Xiaohua Liu
Improved generative adversarial network (Improved GAN) is a successful method of using generative adversarial models to solve the problem of semi-supervised learning.
no code implementations • ICLR 2018 • Alan Do-Omri, Dalei Wu, Xiaohua Liu
In this work, we combine these two ideas and make GANs self-trainable for semi-supervised learning tasks by exploiting their infinite data generation potential.
no code implementations • 19 May 2014 • Dalei Wu, Haiqing Wu
In this paper, we propose a new method based on measuring the dispersion degree (DD) of the training data to avoid this problem, so as to realise automatic robust estimation for MGMMs.