DomainAdversarial Neural Networks DANN
Tags: #machine learning #transfer learningEquation
$$\min [\frac{1}{m}\sum^{m}_{1}\mathcal{L}(f(\textbf{x}^{s}_{i}),y_{i})+\lambda \max(\frac{1}{m}\sum^{m}_{i=1}\mathcal{L}^{d}(o(\textbf{x}^{s}_{i}),1)\frac{1}{m^{'}}\sum^{m^{'}}_{i=1}\mathcal{L}^{d}(o(\textbf{x}^{t}_{i}),0))]$$Latex Code
\min [\frac{1}{m}\sum^{m}_{1}\mathcal{L}(f(\textbf{x}^{s}_{i}),y_{i})+\lambda \max(\frac{1}{m}\sum^{m}_{i=1}\mathcal{L}^{d}(o(\textbf{x}^{s}_{i}),1)\frac{1}{m^{'}}\sum^{m^{'}}_{i=1}\mathcal{L}^{d}(o(\textbf{x}^{t}_{i}),0))]
Have Fun
Let's Vote for the Most Difficult Equation!
Introduction
Equation
Latex Code
\min [\frac{1}{m}\sum^{m}_{1}\mathcal{L}(f(\textbf{x}^{s}_{i}),y_{i})+\lambda \max(\frac{1}{m}\sum^{m}_{i=1}\mathcal{L}^{d}(o(\textbf{x}^{s}_{i}),1)\frac{1}{m^{'}}\sum^{m^{'}}_{i=1}\mathcal{L}^{d}(o(\textbf{x}^{t}_{i}),0))]
Explanation
In this formulation of DomainAdversarial Neural Networks(DANN), authors add a domain adaptation regularizer term to the original loss function of source domain. The domain adaptation regularizer term are calculated based on the Hdivergence of two distributions h(X_{S}) and h(X_{T}). The adversial network aims to maximize the likelihood that the domain classifier are unable to distingush a data point belongs to source domain S or target domain T. Function o(.) is the domain regressor which learns high level representation o(X) given input X. You can check more detailed information in this paper by Hana Ajakan, Pascal Germain, et al., DomainAdversarial Neural Networks for more details.
Related Documents
Related Videos
Discussion
Comment to Make Wishes Come True
Leave your wishes (e.g. Passing Exams) in the comments and earn as many upvotes as possible to make your wishes come true

Nancy AndersonPassing this test is crucial for me.Paula Burton reply to Nancy AndersonYou can make it...20230201 00:00 
Frank CollinsWorking hard in hopes of passing this test.Curtis Price reply to Frank CollinsGooood Luck, Man!20231030 00:00 
Curtis PriceLet's hope I can clear this exam.Zachary Mason reply to Curtis PriceGooood Luck, Man!20230208 00:00
Reply