Automatic generation of facial images has been well studied after the Generative Adversarial Network(GAN) came out. There exists some attempts applying the GAN model to the problem of generating facial images of anime characters, but none of the existing work gives a promising result. In this work, we explore the training of GAN models specialized on an anime facial image dataset. We address th...

language acquisition is a varied field, and there is an ocean of approaches from which one can investigate first/second language acquisition. these approaches root in different fields, basically linguistics. as for linguistics, research in language acquisition ranges from structural and generative-transformational to cognitive linguistics. while in contrast with each other in main respects theo...

In this paper, we propose a family of kernels for the data distributions belonging to the exponential family. We call these kernels generative kernels because they take into account the generative process of the data. Our proposed method considers the geometry of the data distribution to build a set of efficient closed-form kernels best suited for that distribution. We compare our generative ke...

This paper investigates on the possible advantages of applying generative programming in a component based development process: if a component oriented approach is applied, then generative programming can be used to automatically compose and assemble components. In part one of this paper, I present the application of Generative Programming from an engineering point of view, using a simple but c...

We present a higher-order module system similar to those found in Standard ML and Objective Caml. Our system allows both generative and non-generative types. Unlike other systems, the generativity of a type is reflected directly in the signature of the module in which it is declared, allowing a more direct analysis of type abstraction and generativity. Our module system can express both generat...