|
所在平台: Coursera |
课程主页: https://www.coursera.org/learn/sequence-models-tensorflow-gcp
课程评论：没有评论
课程名称：时间序列与自然语言处理的序列模型 课程概述：本课程介绍序列模型及其应用，包括序列模型架构的概述以及如何处理可变长度的输入。课程内容包括： - 预测时间序列的未来值 - 对自由形式文本进行分类 - 使用循环神经网络（RNNs）处理时间序列和文本问题 - 在RNN和LSTM与更简单模型之间进行选择 - 在文本问题中训练和重用词嵌入 学员将通过实践构建和优化自己的文本分类和序列模型，在多个公共数据集上进行实验。 先修课程：基础的SQL，熟悉Python和TensorFlow。 课程大纲： 1. 课程介绍：讲解学习自然语言处理的原因，并提供课程结构和目标的概述。 2. Google Cloud上的自然语言处理：介绍Google Cloud上的自然语言处理架构，探索历史、API（如Dialogflow API）以及解决方案（如Contact Center AI与Document AI）。 3. 使用Vertex AI进行自然语言处理：探讨使用AutoML和自定义训练开发自然语言处理项目的两个选项，并介绍端到端的自然语言处理工作流程，以及应用该工作流程解决文本分类任务的实践实验。 4. 文本表示：描述准备文本数据的过程，并介绍主要文本表示技术的类别。 5. 自然语言处理模型：描述不同的自然语言处理模型，包括ANN、DNN、RNN、LSTM和GRU，介绍每种模型的优缺点。 6. 高级自然语言处理模型：介绍自然语言处理中的前沿技术和模型，如编码器-解码器、注意力机制、变换器、BERT及大型语言模型。 7. 课程总结：回顾课程涵盖的话题，并提供进一步学习的额外资源。
Name:Course introduction
Description:This module addresses the reasons to learn NLP from Google and provides an overview of the course structure and goals.
Name:NLP on Google Cloud
Description:This module introduces the NLP architecture on Google Cloud. It explores the NLP history, the NLP APIs such as the Dialogflow API, and the NLP solutions such as Contact Center AI and Document AI.
Name:NLP with Vertex AI
Description:This module explores AutoML and custom training, which are the two options to develop an NLP project with Vertex AI. Additionally, the module introduces an end-to-end NLP workflow and provides a hands-on lab to apply the workflow to solve a task of text classification with AutoML.
Name:Text representatation
Description:This module describes the process to prepare text data in NLP and introduces the major categories of text representation techniques.
Name:NLP models
Description:This module describes different NLP models including ANN, DNN, RNN, LSTM, and GRU. It also introduces the benefits and disadvantages of each model.
Name:Advanced NLP models
Description:This module introduces the state-of-the-art technologies and models in NLP: encoder-decoder, attention mechanism, transformers, BERT, and large language models.
Name:Course summary
Description:This module reviews the topics covered in the course and provides additional resources for further learning.
This course is an introduction to sequence models and their applications, including an overview of sequence model architectures and how to handle inputs of variable length. • Predict future values of a time-series • Classify free form text • Address time-series and text problems with recurrent neural networks • Choose between RNNs/LSTMs and simpler models • Train and reuse word embeddings in text problems You will get hands-on practice building and optimizing your own text classification and sequence models on a variety of public datasets in the labs we’ll work on together. Prerequisites: Basic SQL, familiarity with Python and TensorFlow
