Natural Language Processing - Deep Learning Models in Python

Natural Language Processing - Deep Learning Models in Python

by Lazy Programmer
Released June 2024
Publisher(s): Packt Publishing
ISBN: 9781836208013

Watch it now on the O’Reilly learning platform with a 10-day free trial.

O’Reilly members get unlimited access to books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.

Start your free trial

Video description

Embark on a journey into Natural Language Processing (NLP) with a focus on deep learning models using Python. The course starts with an introduction to neurons, explaining how they form the basic building blocks of neural networks. You will learn to fit lines and prepare classification codes, culminating in practical text classification tasks using TensorFlow.

Progressing to Feedforward Artificial Neural Networks (ANNs), you will delve into forward propagation, activation functions, and multiclass classification. The course includes extensive code preparation for text classification in TensorFlow, covering text preprocessing, embeddings, and advanced techniques like Continuous Bag of Words (CBOW). This section ensures you understand the geometrical aspects and hyperparameter tuning.

The course then explores Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs), crucial for advanced NLP tasks. You will learn the intricacies of convolutions, CNN architecture, and their application to text. The RNN section covers simple RNNs, GRUs, and LSTMs, with hands-on exercises in text classification, parts-of-speech tagging, and named entity recognition in TensorFlow. Each section is designed to build your skills progressively, ensuring a deep understanding of both theoretical concepts and practical applications.

What you will learn

  • Develop a solid understanding of neural networks and their applications in NLP.
  • Implement text classification models using TensorFlow.
  • Master advanced NLP techniques like embeddings and named entity recognition.
  • Apply convolutional and recurrent neural networks to real-world NLP tasks.
  • Optimize model performance through effective hyperparameter tuning.
  • Advanced techniques like CBOW and hyperparameter tuning.

Audience

This course is designed for data scientists, machine learning engineers, and AI enthusiasts with a basic understanding of Python and machine learning. Familiarity with basic neural network concepts is beneficial but not mandatory.

About the Author

Lazy Programmer: The Lazy Programmer, a distinguished online educator, boasts dual master's degrees in computer engineering and statistics, with a decade-long specialization in machine learning, pattern recognition, and deep learning, where he authored pioneering courses. His professional journey includes enhancing online advertising and digital media, notably increasing click-through rates and revenue. As a versatile full-stack software engineer, he excels in Python, Ruby on Rails, C++, and more. His expansive knowledge covers areas like bioinformatics and algorithmic trading, showcasing his diverse skill set. Dedicated to simplifying complex topics, he stands as a pivotal figure in online education, adeptly navigating students through the nuances of data science and AI.

Table of contents

  1. Chapter 1 : Welcome
    1. Introduction and Outline
    2. Special Offer
  2. Chapter 2 : Getting Set Up
    1. Where To Get the Code
    2. How To Succeed in This Course
  3. Chapter 3 : The Neuron
    1. The Neuron - Section Introduction
    2. Fitting a Line
    3. Classification Code Preparation
    4. Text Classification in Tensorflow
    5. The Neuron
    6. How does a model learn?
    7. The Neuron - Section Summary
  4. Chapter 4 : Feedforward Artificial Neural Networks
    1. ANN - Section Introduction
    2. Forward Propagation
    3. The Geometrical Picture
    4. Activation Functions
    5. Multiclass Classification
    6. ANN Code Preparation
    7. Text Classification ANN in Tensorflow
    8. Text Preprocessing Code Preparation
    9. Text Preprocessing in Tensorflow
    10. Embeddings
    11. CBOW (Advanced)
    12. CBOW Exercise Prompt
    13. CBOW in Tensorflow (Advanced)
    14. ANN - Section Summary
    15. Aside: How to Choose Hyperparameters (Optional)
  5. Chapter 5 : Convolutional Neural Networks
    1. CNN - Section Introduction
    2. What is Convolution?
    3. What is Convolution? (Pattern Matching)
    4. What is Convolution? (Weight Sharing)
    5. Convolution on Color Images
    6. CNN Architecture
    7. CNNs for Text
    8. Convolutional Neural Network for NLP in Tensorflow
    9. CNN - Section Summary
  6. Chapter 6 : Recurrent Neural Networks
    1. RNN - Section Introduction
    2. Simple RNN / Elman Unit (pt 1)
    3. Simple RNN / Elman Unit (pt 2)
    4. RNN Code Preparation
    5. RNNs: Paying Attention to Shapes
    6. GRU and LSTM (pt 1)
    7. GRU and LSTM (pt 2)
    8. RNN for Text Classification in Tensorflow
    9. Parts-of-Speech (POS) Tagging in Tensorflow
    10. Named Entity Recognition (NER) in Tensorflow
    11. Exercise: Return to CNNs (Advanced)
    12. RNN - Section Summary

Product information

  • Title: Natural Language Processing - Deep Learning Models in Python
  • Author(s): Lazy Programmer
  • Release date: June 2024
  • Publisher(s): Packt Publishing
  • ISBN: 9781836208013