Paper Summary(2019.9-2019.12)Knowledge Graph Trans翻译模型系列: TransE :Translating Embeddings for Modeling Multi-relational Data TransH: Knowledge Graph E ...
NLP论文阅读笔记(Ⅲ)
GraphRel: Modeling Text as Relational Graphs for Joint Entity and Relation Extraction Fu, T.-J., Li, P.-H., & Ma, W.-Y. (2019). GraphRel: Modeling ...
NLP论文阅读笔记(Ⅱ)
Attention is all you need Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., … Polosukhin, I. (2017). Attention is all you ...
NLP论文阅读笔记(Ⅰ)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018). BERT: ...
NAS论文阅读笔记
Neural Architecture Search with Reinforcement Learning Zoph, B., & Le, Q. V. (2016). Neural Architecture Search with Reinforcement Learning. 1–16. ...
神经网络结构搜索综述笔记
NAS_Survey_Notes_Ⅰ Elsken, T., Metzen, J. H., & Hutter, F. (2019). Neural Architecture Search. 20, 63–77. https://doi.org/10.1007/978-3-030-05318- ...
自动化机器学习综述笔记
Auto Machine Learning Survey Notes(Ⅰ) Paper Name: Yao, Q., Wang, M., Chen, Y., Dai, W., Yi-Qi, H., Yu-Feng, L., … Yang, Y. (2018). Taking Human out of ...
机器学习读书笔记(Ⅰ)
Notes on Machine Learning重要名词解释Important Expressions训练集train set: 用于模型训练的数据集 验证集validation set:用于进行模型评估和模型选择的数据集 测试集test set:用来评估模型在实际使用中的泛化能力 形象上来说训 ...
深度学习读书笔记(Ⅰ)
Deep Learning Book Notes深度前馈网络deep feedforward network基于梯度的学习——代价函数: 使用最大似然学习条件分布。大多数现代的神经网络使用最大似然来训练。这意味着代价函数就是负的对数似然,它与训练数据和模型分布间的交叉熵等价。 均方误差和平均绝对误 ...