NLP Intro for Text - Sentiment Analysis with Deep Learning

NLP Intro for Text - Sentiment Analysis with Deep Learning - Course Overview

Welcome to this deeplizard course on NLP Intro for Text - Sentiment Analysis with Deep Learning!

This course provides an introduction to the field of Natural Language Processing (NLP) with a focus on sentiment analysis and text classification using artificial neural networks.

At the intersection of linguistics, computer science, and artificial intelligence lies the vast subfield of Natural Language Processing, otherwise known simply as NLP. The focus of NLP is human-machine interaction.

The field of NLP uses multiple algorithms to solve various tasks made up of many different data types.

Given the vast differences between tasks, algorithms, and data types in this field, the way that we work with and process the data to complete these tasks varies greatly between them.

In this course, the type of data we'll be working with is textual data, the type of algorithms that we'll be using to process this data is artificial neural networks, and the particular types of tasks we'll be focusing on fall under text classification for sentiment analysis.

What You'll Learn

In this course, we'll first learn all the fundamental topics required to understand text classification with neural networks. We'll then move on to implementing everything we learned in code across two neural network APIs, TensorFlow and PyTorch.

By taking this course, you will:

• Get introduced to the vast field of Natural Language Processing
• Learn where text classification & sentiment analysis fall in the field of NLP
• Understand how neural networks can be used for NLP tasks
• Learn N-gram model architecture and how it processes text data
• Learn Sequence model architecture and how it processes text data
• Understand what tokenization is and how its applied to text
• Understand what vectorization is and how its applied to text
• Gain an understanding for TF-IDF text vectorization
• Understand how standardization and normalization techniques are applied to text
• Learn about word embeddings and how they work to encode text
• Understand how to use a MLP as an N-gram model for text classification
• Understand how to use a CNN as an Sequence model for text classification
• Gain an understanding for how 1D convolutions process text data
• Develop complete sentiment analysis projects in code with both PyTorch and TensorFlow
• Learn how to programmatically organize a text dataset for neural network training
• Gain experience of implementing text classification neural networks in code
• Understand how to preprocess text data in code
• Learn how to train and evaluate text classification networks in code
• Much more!

Be sure to check out the syllabus for full details about all the topics will cover in this course.

Course Resources

This course has plenty of resources to ensure your success. This is a premium course, and so to gain access to the contents, you must first register.

By registering for the course, you will unlock lifetime access to:

• 26 ad-free 4K video lessons
• 52 pages of fully written corresponding lecture notes
• Download access to all code files used in this course
• Custom-made quizzes following each lesson
• The deeplizard Discord server with exclusive access to the course channel
• Customized visual graphics created for this course

How to register for the course

Registration consists of two steps: creating an account on deeplizard.com and purchasing the course.

1. Create a deeplizard account.
1. Click the Login link on the top right of any page of deeplizard.com.
2. Click create account.
3. Enter a valid email address and password.
4. Enter the verification code sent to your email address.
2. Purchase the course.
1. Ensure you're logged in to deeplizard.com.
2. Browse to the course page.
3. Click the Enroll button.
4. Agree to the Terms and Conditions.
5. Enter your payment details. If you have a discount code, you may enter it here.
6. Upon successful payment, the course will become unlocked, and you may view the full contents.

Technologies used in this course

This course will use the most popular and efficient technologies for coding and communication.

Python

All code in this course is written in Python, an open-source programming language ranking the most popular language for data science and machine learning.

Jupyter Notebook

All Python code will be written within Jupyter Notebook, an intuitive web-based interactive computational environment for creating Python programs. We'll have the option to run the notebooks in a local environment or in a Google Colab environment.

By registering for the course, you will gain access to the fully written notebooks used throughout this course.

PyTorch and TensorFlow

Code projects in this course will be completed using the top two most popular machine learning libraries:

• PyTorch
• TensorFlow

PyTorch is a free and open-sourced machine learning library developed by Facebook's AI Research lab (FAIR), and is heavily used for training and inference of deep neural networks.

Similarly, TensorFlow is also a free and open-sourced machine learning library with a focus on deep neural networks and was developed by the Google Brain team.

Often times, one may tend to choose a single API, label it as their "favorite," and stick with it. We like the idea of learning a concept fundamentally first, and then implementing it across APIs. This not only gives us further programming experience across libraries that may be of interest to potential employers, but also strengthens our understanding of the underlying concept as we implement it in multiple ways.

This is why the code projects and demos in the course will be implemented across both PyTorch and TensorFlow from start to finish.

Discord

By registering for the course, students will gain access to the course channel of the deeplizard Discord server. This is a chat environment where you can discuss the course and other topics of interest, exchange ideas, and collaborate.

Course Prerequisites

Now let's discuss the prerequisites that are required for this course.

• Basic understanding of deep learning and neural networks
• Basic coding skills
• Basic Python experience
• Neural Network API experience (recommended, not required)

If you are brand new to deep learning, then it is recommended that you start with our Deep Learning Fundamentals course first, as we'll be building on these fundamental concepts to form our understanding of how we can use artificial neural networks for text classification tasks.

The Deep Learning Fundamentals course will teach you everything you need to know to get acquainted with all the major deep learning concepts. You can then take your newly gained knowledge from that course, and come to apply it in this one.

Later in the course, we'll jump into code projects, implemented both in TensorFlow and PyTorch, to apply what we've learned about text processing and classification.

We'll be going step-by-step through the code when we get there, but in regards to coding prerequisites, some basic coding skills and Python experience are needed.

It's also recommended, but not necessarily required, to have experience with a neural network API, like PyTorch or TensorFlow. You can check out our courses for these APIs to get acquainted with how they work before we implement our code projects later in the course.

Course Syllabus

Below we have the course syllabus that outlines all of the topics we'll cover in this course. Check out the course page for more details on each lesson.

• Part 1: Introduction to NLP and Text Classification
• Section 1: Intro to Text Classification Models
• Intro to Natural Language Processing
• Text Classification with Neural Networks
• N-Gram Bag Of Words Vs. Sequence Models For Text Classification
• Section 2: N-gram Models
• N-gram Model Preprocessing - Tokenization and Vectorization
• N-gram Model MLP Neural Network Architecture
• Section 3: Sequence Models
• Sequence Model Preprocessing - Tokenization and Vectorization
• Word Embeddings for Neural Networks
• Sequence Model Convolutional Neural Network Architecture
• How Convolutional Neural Networks Process Text Data
• Part 2: Text Classification Sentiment Analysis Project
• Section 1: TensorFlow N-gram Model Code Implementation
• Sentiment Analysis Project Intro - Prerequisites And Dataset
• Organize & Explore Dataset For N-Gram Model
• Text Preprocessing For N-Gram Model
• Build And Train N-Gram Model
• Section 2: TensorFlow Sequence Model Code Implementation
• Organize & Explore Dataset For N-Gram Model
• Text Preprocessing For N-Gram Model
• Build And Train N-Gram Model
• Section 3: PyTorch N-gram Model Code Implementation
• Organize & Explore Dataset For N-Gram Model
• Text Preprocessing For N-Gram Model
• Build N-Gram Model
• Train & Evaluate N-Gram Model
• Section 4: PyTorch Sequence Model Code Implementation
• Organize & Explore Dataset For Sequence Model
• Text Preprocessing For Sequence Model
• Build Sequence Model
• Train & Evaluate Sequence Model
• Course Conclusion

I hope you're looking forward to the course! Let's jump in!