پیشنهاد فرادرس

آموزش داده کاوی متن با پایتون و یادگیری ماشینی

دسته بندی ها: آموزش پایتون (Python) ، آموزش های Packtpub ، هوش مصنوعی ، یادگیری ماشینی (Machine Learning)

داده Text یکی از مهم ترین انواع داده در علم داده است. پیشرفت های جدید در یادگیری ماشینی و تکنیک های یادگیری عمیق در حال حاضر امکان ایجاد محصولات داده های فوق العاده را در منابع متن فراهم می کند. در این دوره با درک اصول متن کاوی مدرن، استفاده از یادگیری ماشینی برای استخراج اطلاعات از متن، کار بر روی Skip-grams، CBOW و X2Vec و غیره آشنا می شوید. در پایان دوره، شما جنبه های مختلف استخراج متن با ML و فرایندهای مهم در آن را خواهید آموخت.

سرفصل:

  • معرفی دوره
  • درک متن کاوی
  • راه اندازی محیط کار
  • خواندن و فرآیند ویژگی های متن
  • درک منابع داده متن
  • N-Grams
  • استخراج از متن
  • استفاده از مدل های ازپیش آموزش دیده
  • طبقه بندی متن
  • الگوریتم های یادگیری ماشین برای طبقه بندی متن
  • نقش های Thumb
  • رویکرد یادگیری عمیق در طبقه بندی متن
  • Word Embeddings
  • Word Embeddings چیست؟
  • آموزش مدل Word2Vec
  • X2Vec
  • و غیره
به این نوشته امتیاز دهید 1 2 3 4 5 بدون امتیاز
Text Mining with Machine Learning and Python [Video] Publisher:Packtpub Author:Thomas Dehaene Duration:2 hours and 26 minutes

Get high-quality information from your text using Machine Learning with Tensorflow, NLTK, Scikit-Learn, and Python
Text is one of the most actively researched and widely spread types of data in the Data Science field today. New advances in machine learning and deep learning techniques now make it possible to build fantastic data products on text sources. New exciting text data sources pop up all the time. You'll build your own toolbox of know-how, packages, and working code snippets so you can perform your own text mining analyses.
You'll start by understanding the fundamentals of modern text mining and move on to some exciting processes involved in it. You'll learn how machine learning is used to extract meaningful information from text and the different processes involved in it. You will learn to read and process text features. Then you'll learn how to extract information from text and work on pre-trained models, while also delving into text classification, and entity extraction and classification. You will explore the process of word embedding by working on Skip-grams, CBOW, and X2Vec with some additional and important text mining processes. By the end of the course, you will have learned and understood the various aspects of text mining with ML and the important processes involved in it, and will have begun your journey as an effective text miner.
The code bundle for this video course is available at https://github.com/PacktPublishing/Text-Mining-with-Machine-Learning-and-Python
Style and Approach
A practical guide demonstrating how to extract information easily using Jupyter notebooks, Anaconda, modern packages, and tools/frameworks such as NLTK, Spacy, Gensim, Scikit-learn, Tensorflow (for CPU), and Python-CRFSuite.
Released: Monday, April 30, 2018
Getting Started with Text Mining
The Course Overview
Understanding Modern-Day Text Mining
Exploring Your Text Mining Toolbox
Setting Up Your Working Environment
A Short Rundown of the Topics We Will Cover
Reading and Processing Text Features
Understanding Text Data Sources
Cleaning Messy Text
Tokenization, POS Tagging, and Lemmatization
Dealing with N-Grams
Extracting from Text
Word Search Versus Entity Extraction
Named Entity Recognition (NER)
Using Pre-Trained Models
Training Your Own NER
Deep Learning Approach to NER
Classification of Text
Feature Representation
Machine Learning Algorithms for Text Classification
Setting Up a Basic Text Classifier
Pitfalls and Rules of Thumb
Putting Classifiers into Production
Deep Learning Approach to Text Classification
Word Embeddings
What Are Word Embeddings?
Main Techniques
Training a Word2Vec Model
Visualizing a Trained Word Embedding Model
X2Vec
Other ML Topics with Text
Stitching It All Together
Topic Modelling
Text Generation
Machine Translation
Further Reading
Closing

پیشنهاد فرادرس

لینک های دانلود حجم فایل: 277.0MB Packtpub Text Mining with Machine Learning and Python [Video]_git.ir.rar