![](https://img-blog.csdnimg.cn/20201014180756926.png?x-oss-process=image/resize,m_fixed,h_64,w_64)
ML读书笔记
文章平均质量分 92
CrazyTensor
致力于创造一只会说话的机器狗
展开
-
2020重新启航
精读Paper&Book 201712 - Transformer - Attention Is All You Need 201810 - BERT - Pre-training of Deep Bidirectional Transformers for Language Understanding 201907 - RoBERTa - A Robustly Optimized BE...原创 2020-01-27 16:44:45 · 301 阅读 · 0 评论 -
机器学习笔记一:概述
机器学习的公认定义[Mitchell, 1997]: A computer program is said to learn from experience E with respect to some class of tasks T and performance measure P if its performance at tasks in T, as measured by P,...原创 2018-05-06 21:14:11 · 331 阅读 · 0 评论 -
Top 2 Language Models
ULMFiT/AWD-LSTM 2018年语言模型预训练特定任务迁移学习的nlp新范式开始成为主流,ULMFiT(Universal Language Model Fine-tuning for Text Classification)是开山鼻祖之一。模型流程如下,包括基础语言模型训练,目标语言模型迁移,分类器微调,语言模型是基于AWD-LSTM(Regularizing and Optimizi...原创 2019-06-25 16:45:39 · 491 阅读 · 0 评论 -
Tensorflow 2.0 学习资料
A machine learning platform from the future. A core principle of Keras is “progressive disclosure of complexity”: it’s easy to get started, and you can gradually dive into workflows where you write mo...原创 2019-10-07 16:44:45 · 429 阅读 · 0 评论