UDA refers to a set of transfer learning methods for transferring knowledge learned from th source domain to the target domain under the assumption of domain discrepancy. Domain adaptation generally assumes that the two domains have the same conditional distributions, but different marginal distributions. 1. Resource Paper List: https://github.com/zhaoxin94/awesome-domain-adaptation Project List: https://github.com/jindongwang/transferlearning Na J, Jung H, Chang H J, et al. FixBi: Bridging Domain Spaces for Unsupervised Domain Adaptation[C] //Proceedings

1. KeyValue dict.clear() 删除字典内所有元素 dict.copy()返回一个字典的浅复制 [dict.fromkeys(seq, val])创建一个新字典，以序列 seq 中元素做字典的键，val 为字典所有键对

Few-shot classification aims to learn a classifier to recognize unseen classes during training with limited labeled examples. meta-learning paradigm: transferable knowledge is extracted and propagated from a collection of tasks to prevent over fitting and improve generalization. model initialization based methods; metric learning methods hallucination based methods directly predicting the weighs of the classifiers for novel classes Relative Work Initialization based methods: good model initialization: to learn to fine-tune, learn with limited number of labeled examples and small number of gradient update steps; learning an optimizer: LSTM-based meta-learner for replacing the stochastic gradient decent optimizer.

Alvarez, Raziel, and Hyun-Jin Park. “End-to-end streaming keyword spotting.” ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2019. keywords: keyword Paper: keywrod spotting Summary an efficient memorized neural network topology that aims at making better use of the parameters and associated computations in the DNN by holding a memory of previous activations distributed over the depth of DNN. a method to train the DNN, to produce the keyword spotting score.

1. FinBert 网络结构：其中前者采用了 12 层 Transformer 结构，后者采用了 24 层 Transformer 结构。 训练语料： 金融财经类新闻：从公开渠道采集的最近十年的金融财经类新闻资讯，约 100 万

Chen, Xieyuanli, Thomas Läbe, Lorenzo Nardi, Jens Behley, and Cyrill Stachniss. “Learning an Overlap-based Observation Model for 3D LiDAR Localization.” Paper: Overlap-based Summary 文章使用了OverlapNet作为蒙特卡洛定位算法（MCL）的观测模型，实现了基于激光