Udemy Natural Language Processing & Deep Learning: Zero to Hero

Linguistics & Machine Learning: Grammar Syntax, Sentiment, ScrapeTweets, RNN/LSTM,Chatbot, SQuAD, Summary, Audio To Text


What you'll learn

• Libraries: NLTK, Hugging Face, SpaCy, Sci-kit Learn, Tensorflow, Pytorch, Twint
• Linguistics Foundation To Help Learn NLP Concepts
• Deep Learning: Neural Networks, RNN, LSTM Theory & Practical Projects
• Scrape Unlimited Tweets Using An Open Source Intelligence Tool
• Machine Reading Comprehension: Create A Question Answering System with SQuAD
• No Tedious Anaconda or Jupyter Installs: Use Modern Google Colab Cloud-Based Notebooks for using Python
• How To Build Generative AI Chatbots
• Create A Netflix Recommendation System With Word2Vec
• Perform Sentiment Analysis on Steam Game Reviews
• Convert Speech To Text
• Machine Learning Modelling Techniques
• Markov Property - Theory & Practical
• Optional Python For Beginners Section
• Cosine-Similarity & Vectors
• Word Embeddings: My Favourite Topic Taught In Depth
• Speech Recognition
• LSTM Fake News Detector
• Context-Free Grammar Syntax
• Scrape Wikipedia & Create An Article Summarizer

Show less


Requirements

• No Tedious Installs
• No previous programming knowledge necessary. The lectures slowly explain the python syntax as you code alone with me.
• New to Python: you get explanations of the code as you code along with me but not only that - theory slides explain concepts to help you understand what's going on behind the code.
• No data science knowledge required: lectures teach how to work with data and key modelling concepts.
• No NLP knowledge required. Linguistic concepts are taught to give a strong foundation of NLP even before you get into practical coding. This helps you to grasp NLP modelling techniques and cleaning concepts better.

Description
This course takes you from a beginner level to being able to understand NLP concepts, linguistic theory, and then practice these basic theories using Python - with very simple examples as you code along with me.
Get experience doing a full real-world workflow from Collecting your own Data to NLP Sentiment Analysis using Big Datasets of over 50,000 Tweets.

• Data collection: Scrape Twitter using: OSINT - Open Source Intelligence Tools: Gather text data using real-world techniques. In the real world, in many instances you would have to create your own data set; i.e source your data instead of downloading a clean, ready-made file online
• Use Python to search relevant tweets for your study and NLP to analyze sentiment.

Language Syntax: Most NLP courses ignore the core domain of Linguistics. This course explains the fundamentals of Language Syntax & Parse trees - the foundation of how a machine can interpret the structure of s sentence.
New to Python: If you are new to Python or any computer programming, the course instructions make it easy for you to code together with me. I explain code line by line.
No Installs, we go straight to coding - Code using Google Colab - to be up-to-date with what's being used in the Data Science world 2021!
The gentle pace takes you gradually from these basics of NLP foundation to being able to understand Mathematical & Linguistic (English-Language-based, Non-Mathematical) theories of Deep Learning.
Natural Language Processing Foundation

• Linguistics & Semantics - study the background theory on natural language to better understand the Computer Science applications
• Pre-processing Data (cleaning)
• Regex, Tokenization, Stemming, Lemmatization
• Name Entity Recognition (NER)
• Part-of-Speech Tagging

Libraries:

• NLTK
• Sci-kit Learn
• Tensorflow
• Pytorch
• SpaCy
• DeepPavlov
• Twint

The topics outlined below are taught using practical Python projects!

• Parse Tree
• Markov Chain
• Text Classification & Sentiment Analysis
• Company Name Generator
• Unsupervised Sentiment Analysis
• Topic Modelling
• Word Embedding with Deep Learning Models
• Open Domain Question Answering (like asking Google)
• Closed Domain Question Answering (Like asking a Restaurant-Finder bot)
• LSTM using TensorFlow, Keras Sequence Model
• Speech Recognition
• Convert Speech to Text

Neural Networks

• This is taught from first principles - comparing Biological Neurons in the Human Brain to Artificial Neurons.
• Practical project: Sentiment Analysis of Steam Reviews

Word Embedding: This topic is covered in detail, similar to an undergraduate course structure that includes the theory & practical examples of:

• TF-IDF
• Word2Vec
• One Hot Encoding
• gloVe

Deep Learning

• Recurrent Neural Networks
• LSTMs
  • Get introduced to Long short-term memory and the recurrent neural network architecture used in the field of deep learning.
  • Build models using LSTMs

Who this course is for:

• Anyone who is curious about data science & NLP
• Those who are in the Business & Marketing world - learn use NLP to gain insight into customers & products. Can help at interviews & job promotions.
• If you intend to enrol in an NLP/Data Science course but are a total newbie, complete this course before to avoid being lost in class since it can seem overwhelming if classmates already have a foundation in Python or Datascience.