Knowledge distillation between machine learning models has opened many new avenues for parameter count reduction, performance improvements, or amortizing training time when changing architectures the teacher and student network. In case of reinforcement learning, this technique also been applied to distill policies students. Until now, policy required access a simulator real world trajectories....

Recent work in discourse semantics has focused on modeling the determinants of meaning for linguistic utterances beyond the level of a single clause. As more parameters of interpretation have been incorporated into our model of meaning, the assumption sregarding compositionality have become much more complex (cf. Groenendijk and Stokhof 1990; Kamp and Reyle 1993; Asher 1993; Asher and Lascaride...

REFERENCES 1. H. K Khalil. Non-linear Systems. Prentice-Hall, New Jersey, 1996. 2. L. Metz, et al., Unrolled generative adversarial networks. (ICLR 2017) 3. M. Heusel et al., GANs trained by a TTUR converge to a local Nash equilibrium (NIPS 2017) 4. I. J. Goodfellow et al., Generative Adversarial Networks (NIPS 2014) An increasingly popular class of generative models — models that “understand” ...

Based on the previous work by the Design Technology Research Centre in the School of Design of the Hong Kong polytechnic University, we have developed a new generative design framework for the development of creative cultural industries for western China as a collaborative initiative among the Hong Kong Polytechnic University, Xian Jiaotong University, Xian Tongli International college, Cultura...

In this paper, a novel strategy of Secure Steganograpy based on Generative Adversarial Networks is proposed to generate suitable and secure covers for steganography. The proposed architecture has one generative network, and two discriminative networks. The generative network mainly evaluates the visual quality of the generated images for steganography, and the discriminative networks are utiliz...

Generative strategies, where learners process the target content while connecting different concepts to build a knowledge network, has shown potential to improve student learning outcomes. While concept maps in particular have been linked to the development of generative strategies, few studies have explored structuring the concept mapping process to support generative strategies, and few studi...

Deep generative models (DGMs) are effective on learning multilayered representations of complex data and performing inference of input data by exploring the generative ability. However, little work has been done on examining or empowering the discriminative ability of DGMs on making accurate predictions. This paper presents max-margin deep generative models (mmDGMs), which explore the strongly ...

We present a conditional generative model to learn variation in cell and nuclear morphology and the location of subcellular structures from microscopy images. Our model generalizes to a wide range of subcellular localization and allows for a probabilistic interpretation of cell and nuclear morphology and structure localization from fluorescence images. We demonstrate the effectiveness of our ap...