会说话的机器狗

精读Paper&Book201712 - Transformer - Attention Is All You Need201810 - BERT - Pre-training of Deep Bidirectional Transformers for Language Understanding201907 - RoBERTa - A Robustly Optimized BE...

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,...

ULMFiT/AWD-LSTM2018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...

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...