4.51 out of 5
4.51
1929 reviews on Udemy

Deep Learning and NLP A-Z™: How to create a ChatBot

Learn the Theory and How to implement state of the art Deep Natural Language Processing models in Tensorflow and Python
Instructor:
Hadelin de Ponteves
12,960 students enrolled
English [Auto-generated] More
Why this is important
Types of Natural Language Processing
Classical vs. Deep Learning Models
End to End Deep Learning Models
Seq2Seq Architecture & Training
Beam Search Decoding

We’ve talked about, speculated and often seen different applications for Artificial Intelligence – But what about one piece of technology that will not only gather relevant information, better customer service and could even differentiate your business from the crowd?

ChatBots are here, and they came change and shape-shift how we’ve been conducting online business. Fortunately technology has advanced enough to make this a valuable tool something accessible that almost anybody can learn how to implement.

If you want to learn one of the most attractive, customizable and cutting edge pieces of technology available, then this course is just for you!

Welcome to the course!

1
Get Excited!
2
Applications
3
BONUS: Learning Paths
4
Some Additional Resources!!
5
This PDF resource will help you a lot!

Deep NLP Intuition

1
What You'll Need For This Module
2
Updates on Udemy Reviews
3
Plan of Attack
4
Types of Natural Language Processing
5
Classical vs Deep Learning Models
6
End-to-end Deep Learning Models
7
Bag-of-words model
8
Seq2Seq Architecture (Part 1)
9
Seq2Seq Architecture (Part 2)
10
Seq2Seq Training
11
Beam Search Decoding
12
Attention Mechanisms (Part 1)
13
Attention Mechanisms (Part 2)

Building a ChatBot with Deep NLP

1
ChatBot - Step 1
2
ChatBot - Step 2
3
ChatBot - Step 3

---------- PART 1 - DATA PREPROCESSING ----------

1
Welcome to Part 1 - Data Preprocessing
2
ChatBot - Step 4
3
ChatBot - Step 5
4
ChatBot - Step 6
5
ChatBot - Step 7
6
ChatBot - Step 8
7
ChatBot - Step 9
8
ChatBot - Step 10
9
ChatBot - Step 11
10
ChatBot - Step 12
11
ChatBot - Step 13
12
ChatBot - Step 14
13
ChatBot - Step 15
14
ChatBot - Step 16
15
ChatBot - Step 17
16
Checkpoint!

---------- PART 2 - BUILDING THE SEQ2SEQ MODEL ----------

1
What You'll Need For This Module
2
Welcome to Part 2 - Building the Seq2Seq Model
3
ChatBot - Step 18

The TensorFlow placeholder function:

https://www.tensorflow.org/api_docs/python/tf/placeholder

4
ChatBot - Step 19

Most important tools used:

https://www.tensorflow.org/api_docs/python/tf/fill

https://www.tensorflow.org/api_docs/python/tf/strided_slice

https://www.tensorflow.org/api_docs/python/tf/concat

5
ChatBot - Step 20

Most important tools used:

https://www.tensorflow.org/api_docs/python/tf/contrib/rnn/BasicLSTMCell

https://www.tensorflow.org/api_docs/python/tf/contrib/rnn/DropoutWrapper

https://www.tensorflow.org/api_docs/python/tf/contrib/rnn/MultiRNNCell

https://www.tensorflow.org/api_docs/python/tf/nn/bidirectional_dynamic_rnn

6
ChatBot - Step 21

Most important tools used:

https://www.tensorflow.org/programmers_guide/embedding

https://www.tensorflow.org/api_docs/python/tf/variable_scope

https://www.tensorflow.org/versions/r1.0/api_docs/python/tf/contrib/seq2seq/prepare_attention

https://www.tensorflow.org/versions/r1.0/api_docs/python/tf/contrib/seq2seq/attention_decoder_fn_train

https://www.tensorflow.org/versions/r1.0/api_docs/python/tf/contrib/seq2seq/dynamic_rnn_decoder

https://www.tensorflow.org/api_docs/python/tf/nn/dropout

7
ChatBot - Step 22

Most important tools used:

https://www.tensorflow.org/programmers_guide/embedding

http://web.stanford.edu/class/cs20si/lectures/notes_04.pdf

https://www.tensorflow.org/api_docs/python/tf/variable_scope

https://www.tensorflow.org/versions/r1.0/api_docs/python/tf/contrib/seq2seq/prepare_attention

https://www.tensorflow.org/versions/r1.0/api_docs/python/tf/contrib/seq2seq/attention_decoder_fn_inference

https://www.tensorflow.org/versions/r1.0/api_docs/python/tf/contrib/seq2seq/dynamic_rnn_decoder

https://www.tensorflow.org/api_docs/python/tf/nn/dropout

8
ChatBot - Step 23

Most important tools used:

https://www.tensorflow.org/api_docs/python/tf/variable_scope

https://www.tensorflow.org/api_docs/python/tf/contrib/rnn/BasicLSTMCell

https://www.tensorflow.org/api_docs/python/tf/contrib/rnn/DropoutWrapper

https://www.tensorflow.org/api_docs/python/tf/contrib/rnn/MultiRNNCell

https://www.tensorflow.org/api_docs/python/tf/truncated_normal_initializer

https://www.tensorflow.org/api_docs/python/tf/zeros_initializer

https://www.tensorflow.org/api_docs/python/tf/contrib/layers/fully_connected

9
ChatBot - Step 24

Most important tools used:

https://www.tensorflow.org/api_docs/python/tf/contrib/layers/embed_sequence

https://www.tensorflow.org/api_docs/python/tf/Variable

https://www.tensorflow.org/api_docs/python/tf/random_uniform

https://www.tensorflow.org/api_docs/python/tf/nn/embedding_lookup

10
Checkpoint!

---------- PART 3 - TRAINING THE SEQ2SEQ MODEL ----------

1
What You'll Need For This Module
2
Welcome to Part 3 - Training the Seq2Seq Model
3
ChatBot - Step 25

Geoffrey Hinton's paper:

https://www.cs.toronto.edu/~hinton/absps/JMLRdropout.pdf

4
ChatBot - Step 26

Most important tools used:

https://www.tensorflow.org/api_docs/python/tf/reset_default_graph

https://www.tensorflow.org/api_docs/python/tf/InteractiveSession

5
ChatBot - Step 27
6
ChatBot - Step 28

The TensorFlow placeholder_with_default function:

https://www.tensorflow.org/versions/r0.12/api_docs/python/io_ops/placeholders#placeholder_with_default

7
ChatBot - Step 29

The TensorFlow shape function:

https://www.tensorflow.org/api_docs/python/tf/shape

8
ChatBot - Step 30

The TensorFlow reverse function:

https://www.tensorflow.org/api_docs/python/tf/reverse

https://docs.scipy.org/doc/numpy-1.13.0/reference/generated/numpy.reshape.html

9
ChatBot - Step 31

Most important tools used:

https://www.tensorflow.org/api_docs/python/tf/name_scope

https://www.tensorflow.org/api_docs/python/tf/contrib/seq2seq/sequence_loss

https://www.tensorflow.org/api_docs/python/tf/ones

https://www.tensorflow.org/api_docs/python/tf/train/AdamOptimizer

https://www.tensorflow.org/versions/r0.12/api_docs/python/train/gradient_clipping

https://www.tensorflow.org/api_docs/python/tf/clip_by_value

10
ChatBot - Step 32
11
ChatBot - Step 33

Difference between return and yield:

http://www.geeksforgeeks.org/use-yield-keyword-instead-return-keyword-python/

12
ChatBot - Step 34
13
ChatBot - Step 35

Most important tools used:

https://www.tensorflow.org/api_docs/python/tf/global_variables_initializer

https://pyformat.info/

14
ChatBot - Step 36
15
Checkpoint!

---------- PART 4 - TESTING THE SEQ2SEQ MODEL ----------

1
What You'll Need For This Module
2
Welcome to Part 4 - Testing the Seq2Seq Model
3
ChatBot - Step 37

Most important tools used:

https://www.tensorflow.org/api_docs/python/tf/InteractiveSession

https://www.tensorflow.org/api_docs/python/tf/global_variables_initializer

https://www.tensorflow.org/api_docs/python/tf/train/Saver

4
ChatBot - Step 38
5
ChatBot - Step 39
6
ChatBot - Step 40
7
Checkpoint!
8
Training the ChatBot on Google Colab with GPU

Learn how to run the Chatbot in a Google Colab notebook with GPU training!

---------- PART 5 - IMPROVING & TUNING THE SEQ2SEQ MODEL ----------

1
ChatBot - Step 41: Improving & Tuning the ChatBot
2
ChatBot - Step 42: Introduction to a new model & setup
3
ChatBot - Step 43: Chatbot model discussion
4
ChatBot - Step 44: Tensorboard
5
ChatBot - Step 45: Run the new chatbot model

Other ChatBot Implementations

1
What You'll Need For This Module
2
The Best ChatBot

Intuition and Code resources for The Best ChatBot:

http://suriyadeepan.github.io/2016-06-28-easy-seq2seq/

http://suriyadeepan.github.io/2016-12-31-practical-seq2seq/

https://github.com/suriyadeepan/practical_seq2seq

3
A ChatBot Implementation in TensorFlow 1.4
4
A ChatBot Implementation in PyTorch
5
THANK YOU bonus video

Annex 1: Artificial Neural Networks

1
Plan of Attack
2
The Neuron
3
The Activation Function
4
How do Neural Networks work?
5
How do Neural Networks learn?
6
Gradient Descent
7
Stochastic Gradient Descent
8
Backpropagation

Annex 2: Recurrent Neural Networks

1
Plan of Attack
You can view and review the lecture materials indefinitely, like an on-demand channel.
Definitely! If you have an internet connection, courses on Udemy are available on any device at any time. If you don't have an internet connection, some instructors also let their students download course lectures. That's up to the instructor though, so make sure you get on their good side!
4.5
4.5 out of 5
1929 Ratings

Detailed Rating

Stars 5
988
Stars 4
636
Stars 3
210
Stars 2
57
Stars 1
38
b94fe5602b461c3e8f31f72fb3e1b3cc
30-Day Money-Back Guarantee

Includes

12 hours on-demand video
17 articles
Full lifetime access
Access on mobile and TV
Certificate of Completion