Fisher GAN
نویسندگان
چکیده
Generative Adversarial Networks (GANs) are powerful models for learning complex distributions. Stable training of GANs has been addressed in many recent works which explore different metrics between distributions. In this paper we introduce Fisher GAN which fits within the Integral Probability Metrics (IPM) framework for training GANs. Fisher GAN defines a critic with a data dependent constraint on its second order moments. We show in this paper that Fisher GAN allows for stable and time efficient training that does not compromise the capacity of the critic, and does not need data independent constraints such as weight clipping. We analyze our Fisher IPM theoretically and provide an algorithm based on Augmented Lagrangian for Fisher GAN. We validate our claims on both image sample generation and semi-supervised classification using Fisher GAN.
منابع مشابه
Structural and optical properties of GaN films grown on GaAs substrates by molecular beam epitaxy
GaN films are grown on [0 0 1] GaAs substrates by plasma-assisted molecular beam epitaxy using a three-step process that consists of a substrate nitridation, deposition of a low-temperature buffer layer, and a high-temperature overgrowth. X-ray diffraction and transmission electron microscopy indicate that this method promotes prismatic growth of c-oriented a-GaN. Photoluminescence studies show...
متن کاملSemi-Supervised Learning with IPM-based GANs: an Empirical Study
We present an empirical investigation of a recent class of Generative Adversarial Networks (GANs) using Integral Probability Metrics (IPM) and their performance for semi-supervised learning. IPM-based GANs like Wasserstein GAN, Fisher GAN and Sobolev GAN have desirable properties in terms of theoretical understanding, training stability, and a meaningful loss. In this work we investigate how th...
متن کاملNon-linear modeling, analysis, design and simulation of a solid state power amplifier based on GaN technology for Ku band microwave application
A new non-linear method for design and analysis of solid state power amplifiers is presented and applied to an aluminum gallium nitride, gallium nitride (AlGaN-GaN) high electron-mobility transistor (HEMTs) on silicon-carbide (SiC) substrate for Ku band (12.4 13.6 GHz) applications. With combining output power of 8 transistors, maximum output power of 46.3 dBm (42.6 W), PAE of 43% and linear ga...
متن کاملوابستگی انرژی گذارهای اپتیکی در نانوساختارهای چاههای کوانتومی GaN/AlGaN به پهنای سد و چاه کوانتومی
Internal polarizations field which take place in quantum structures of group-III nitrides have an important consequence on their optical properties. Optical properties of wurtzite AlGaN/GaN quantum well (QW) structures grown by MBE and MOCVD on c-plane sapphire substrates have been investigated by means of photoluminescence (PL) and time resolved photoluminescence (TRPL) at low-temperature. PL ...
متن کامل