Domain Adaptation Deep Learning

Domain adversarial neural network dann ganin lempitsky 2015 introduces gradient reversal layer to make the source and target distribution similar.

Domain adaptation deep learning. A new deep learning model for fault diagnosis with good anti noise and domain adaptation ability on raw vibration signal wei zhang gaoliang peng chuanhao li yuanhang chen and zhujun zhang state key laboratory of robotics and system harbin institute of technology no 92 xidazhi street. Domain adaptation is a field associated with machine learning and transfer learning this scenario arises when we aim at learning from a source data distribution a well performing model on a different but related target data distribution. Deep learning based machinery fault diagnostics with domain adaptation across sensors at different places abstract.

Therefore multi source domain adaptation mda is needed in order to leverage all of the available data. Adversarial discriminative domain adaptation adda tzeng et al 2017 uses independent source. Domain adaptation by using causal inference to predict invariant conditional distributions. For instance the deep reconstruction classification network drcn tries to solve these two tasks simultaneously.

Because the domain shift not only exists between each source and target but also exists among different sources the source combined data from different sources may interfere with each other during the learning process riemer2019learning. Under review as a conference paper at iclr 2018 domain adaptation for deep reinforcement learning in visually distinct games anonymous authors paper under double blind review abstract many deep reinforcement learning approaches use graphical state representations. Domain adversarial neural network architecture by ganin et al. In the recent years data driven machinery fault diagnostic methods have been successfully developed and the tasks where the training and testing data are from the same distribution have been well addressed.

This approach uses an auxiliary reconstruction task to create a shared representation for each of the domains. Joint domain alignment and discriminative feature learning for unsupervised deep. I classification of the source data and ii reconstruction of.