Applied Deep Learning: Build a Chatbot - Theory, Application

Name: Applied Deep Learning: Build a Chatbot - Theory, Application
Rating: 4.5 (1024 reviews)

Understand the Theory of how Chatbots work and implement them in Python and PyTorch!

Created byFawaz Sammani

Last updated 10/2020

English

What you'll learn

Understand the theory behind Sequence Modeling
Understand the theory of how Chatbots work
Undertand the theory of how RNNs and LSTMs work
Get Introduced to PyTorch
Implement a Chatbot in PyTorch
Undertand the theory of different Sequence Modeling Applications

Course content

8 sections • 42 lectures • 6h 10m total length

BEFORE WE START...........PLEASE READ THIS1:16
Introduction to RNNs Part 110:31
Introduction to RNNs Part 28:21
Test Your Understanding
Playing with the Activations9:25
LSTMs8:47
LSTM Variants3:22
Describe lstm variants where gates use the current input, previous memory, and previous outputs to update the cell state, including a coupled forget-input approach that uses the opposite gate value.
LSTM Step-by-Step Example Walktrough3:38

The Dataset10:13
Processing the Dataset Part 16:34
Process the dataset by parsing each line into a dictionary of fields: line id, character id, movie id, character, and text, and build a line dictionary keyed by line id.
Processing the Data Part 27:42
Processing the Dataset Part 37:51
Processing the Dataset Part 45:43
Processing the Words10:54
Processing the Text9:00
Processing the Text Part 28:42
Filtering the Text6:10
Getting Rid of Rare Words8:33

Preparing the Data for Model Part 111:34
Prepare preprocessed sentences by converting them to word indices via the vocabulary, pad to a maximum length of 10 with zeros, include end-of-sentence tokens, and transpose for batched processing.
Understanding the zip function5:25
Preparing the Data for Model Part 27:10
Preparing the Data for Model Part 39:34
Define a binary matrix converting token indices from vocabulary into a ones and zeros matrix, marking the back token as zero, then prepare input tensors, masks, and lengths with torch.
Preparing the Data for Model Part 412:18

Requirements

Some Basic High School Mathematics
Some Basic Programming Knowledge
Some basic Knowledge about Neural Networks

Description

In this course, you'll learn the following:

RNNs and LSTMs
Sequence Modeling
PyTorch
Building a Chatbot in PyTorch

We will first cover the theoretical concepts you need to know for building a Chatbot, which include RNNs, LSTMS and Sequence Models with Attention.

Then we will introduce you to PyTorch, a very powerful and advanced deep learning Library. We will show you how to install it and how to work with it and with PyTorch Tensors.

Then we will build our Chatbot in PyTorch!

Please Note an important thing: If you don't have prior knowledge on Neural Networks and how they work, you won't be able to cope well with this course. Please note that this is not a Deep Learning course, it's an Application of Deep Learning, as the course names implies (Applied Deep Learning: Build a Chatbot). The course level is Intermediate, and not Beginner. So please familiarize yourself with Neural Networks and it's concepts before taking this course. If you are already familiar, then your ready to start this journey!

Who this course is for:

Anybody enthusiastic about Deep Learning Applications

Applied Deep Learning: Build a Chatbot - Theory, Application

What you'll learn

Explore related topics

Course content

Theory Part 1 - RNNs and LSTMs7 lectures • 45min

Theory Part 2 - Sequence Modeling3 lectures • 30min

Practical Part 1 - Introduction to PyTorch4 lectures • 38min

Practical Part 2 - Processing the Dataset10 lectures • 1hr 21min

Practical Part 3 - Data Preperation5 lectures • 46min

Practical Part 4 - Building the Model6 lectures • 1hr 22min

Practical Part 5 - Training the Model6 lectures • 47min

Deep Learning with Transformers1 lecture • 1min

Requirements

Description

Who this course is for: