CF

Machine Learning: Natural Language Processing in Python (V2)

22h 4m 2s
English
Paid

Welcome to Machine Learning: Natural Language Processing in Python (Version 2). This course covers the use of Markov Models, NLTK, Artificial Intelligence, Deep Learning, Machine Learning, and Data Science in Python.

Course Overview

This is a comprehensive 4-in-1 course covering:

  1. Vector models and text preprocessing methods
  2. Probability models and Markov models
  3. Machine learning methods
  4. Deep learning and neural network methods

Part 1: Vector Models and Text Preprocessing

Discover why vectors are essential in data science and artificial intelligence. Learn techniques for converting text into vectors like CountVectorizer and TF-IDF, as well as neural embedding methods such as word2vec and GloVe.

Applications

  • Text classification
  • Document retrieval / search engine
  • Text summarization

Additionally, master important text preprocessing steps like tokenization, stemming, and lemmatization. Briefly explore classic NLP tasks like parts-of-speech tagging.

Part 2: Probability Models and Markov Models

Learn about a pivotal model used in finance, bioinformatics, and reinforcement learning. Explore how probability models can assist in:

  • Building a text classifier
  • Article spinning
  • Text generation (such as poetry)

Grasp the essentials needed to understand advanced Transformer models like BERT and GPT-3.

Part 3: Machine Learning Methods

Focus on applying machine learning methods to classic NLP tasks such as:

  • Spam detection
  • Sentiment analysis
  • Latent semantic analysis (LSA)
  • Topic modeling

Learn to apply Naive Bayes, Logistic Regression, PCA/SVD, and LDA algorithms significant in NLP.

Part 4: Deep Learning Methods

Enhance your capabilities with modern neural network architectures applicable to NLP tasks. Understand:

  • Feedforward Artificial Neural Networks (ANNs)
  • Embeddings
  • Convolutional Neural Networks (CNNs)
  • Recurrent Neural Networks (RNNs)

Explore RNN architectures like LSTM and GRU, widespread in language processing by leading tech companies. Gain insights into Transformers (BERT, GPT-3) as part of deep neural networks.

About the Author: Udemy

Udemy thumbnail

Udemy is the largest open marketplace for online courses on the internet. Founded in 2010 by Eren Bali, Oktay Caglar, and Gagan Biyani and headquartered in San Francisco, the company went public on the Nasdaq in 2021 under the ticker UDMY. The platform hosts well over two hundred thousand courses across software development, IT and cloud, data science, design, business, marketing, and creative skills, taught by tens of thousands of independent instructors. Roughly seventy million learners use it worldwide, and the corporate arm — Udemy Business — supplies a curated subset of that catalog to enterprise customers.

Because Udemy is a marketplace rather than a single editorial publisher, the catalog is uneven by design. The strongest material lives in the long-form, project-based courses authored by working engineers — full-stack JavaScript, React, Node.js, Python data science, AWS, Docker and Kubernetes, mobile development with Flutter and React Native, and cloud certification preparation. The CourseFlix listing under this source is the slice of that catalog that has been mirrored here for offline-friendly viewing, organized by topic and updated as new releases land. Pricing on Udemy itself swings dramatically with the site's near-permanent sales, which is why the platform is best treated as a deep reference catalog: pick instructors with strong reviews and a track record of updating their material rather than buying on the headline price alone.

Watch Online 152 lessons

This is a demo lesson (10:00 remaining)

You can watch up to 10 minutes for free. Subscribe to unlock all 152 lessons in this course and access 10,000+ hours of premium content across all courses.

View Pricing
0:00
/
#1: Introduction and Outline
All Course Lessons (152)
#Lesson TitleDurationAccess
1
Introduction and Outline Demo
10:41
2
Are You Beginner, Intermediate, or Advanced? All are OK!
05:07
3
Where to get the Code
04:18
4
How to use Github & Extra Coding Tips (Optional)
08:57
5
Vector Models & Text Preprocessing Intro
03:41
6
Basic Definitions for NLP
05:02
7
What is a Vector?
10:42
8
Bag of Words
02:33
9
Count Vectorizer (Theory)
13:46
10
Tokenization
14:46
11
Stopwords
04:52
12
Stemming and Lemmatization
12:04
13
Stemming and Lemmatization Demo
13:27
14
Count Vectorizer (Code)
15:44
15
Vector Similarity
11:36
16
TF-IDF (Theory)
14:17
17
(Interactive) Recommender Exercise Prompt
02:37
18
TF-IDF (Code)
20:26
19
Word-to-Index Mapping
10:55
20
How to Build TF-IDF From Scratch
15:09
21
Neural Word Embeddings
10:16
22
Neural Word Embeddings Demo
11:26
23
Vector Models & Text Preprocessing Summary
03:51
24
Text Summarization Preview
01:22
25
How To Do NLP In Other Languages
10:42
26
Suggestion Box
03:11
27
Probabilistic Models (Introduction)
04:47
28
Markov Models Section Introduction
02:43
29
The Markov Property
07:35
30
The Markov Model
12:31
31
Probability Smoothing and Log-Probabilities
07:51
32
Building a Text Classifier (Theory)
07:30
33
Building a Text Classifier (Exercise Prompt)
06:34
34
Building a Text Classifier (Code pt 1)
10:33
35
Building a Text Classifier (Code pt 2)
12:07
36
Language Model (Theory)
10:16
37
Language Model (Exercise Prompt)
06:53
38
Language Model (Code pt 1)
10:46
39
Language Model (Code pt 2)
09:26
40
Markov Models Section Summary
03:01
41
Article Spinning - Problem Description
07:56
42
Article Spinning - N-Gram Approach
04:25
43
Article Spinner Exercise Prompt
05:46
44
Article Spinner in Python (pt 1)
17:33
45
Article Spinner in Python (pt 2)
10:01
46
Case Study: Article Spinning Gone Wrong
05:43
47
Section Introduction
04:51
48
Ciphers
04:00
49
Language Models (Review)
16:07
50
Genetic Algorithms
21:24
51
Code Preparation
04:47
52
Code pt 1
03:07
53
Code pt 2
07:21
54
Code pt 3
04:53
55
Code pt 4
04:04
56
Code pt 5
07:13
57
Code pt 6
05:26
58
Cipher Decryption - Additional Discussion
02:57
59
Section Conclusion
06:01
60
Machine Learning Models (Introduction)
05:51
61
Spam Detection - Problem Description
06:33
62
Naive Bayes Intuition
11:38
63
Spam Detection - Exercise Prompt
02:08
64
Aside: Class Imbalance, ROC, AUC, and F1 Score (pt 1)
12:26
65
Aside: Class Imbalance, ROC, AUC, and F1 Score (pt 2)
11:03
66
Spam Detection in Python
16:24
67
Sentiment Analysis - Problem Description
07:28
68
Logistic Regression Intuition (pt 1)
17:37
69
Multiclass Logistic Regression (pt 2)
06:53
70
Logistic Regression Training and Interpretation (pt 3)
08:16
71
Sentiment Analysis - Exercise Prompt
04:01
72
Sentiment Analysis in Python (pt 1)
10:39
73
Sentiment Analysis in Python (pt 2)
08:29
74
Text Summarization Section Introduction
05:35
75
Text Summarization Using Vectors
05:31
76
Text Summarization Exercise Prompt
01:51
77
Text Summarization in Python
12:41
78
TextRank Intuition
08:04
79
TextRank - How It Really Works (Advanced)
10:51
80
TextRank Exercise Prompt (Advanced)
01:24
81
TextRank in Python (Advanced)
14:34
82
Text Summarization in Python - The Easy Way (Beginner)
06:07
83
Text Summarization Section Summary
03:23
84
Topic Modeling Section Introduction
03:08
85
Latent Dirichlet Allocation (LDA) - Essentials
10:55
86
LDA - Code Preparation
03:42
87
LDA - Maybe Useful Picture (Optional)
01:53
88
Latent Dirichlet Allocation (LDA) - Intuition (Advanced)
14:55
89
Topic Modeling with Latent Dirichlet Allocation (LDA) in Python
11:39
90
Non-Negative Matrix Factorization (NMF) Intuition
10:22
91
Topic Modeling with Non-Negative Matrix Factorization (NMF) in Python
05:34
92
Topic Modeling Section Summary
01:38
93
LSA / LSI Section Introduction
04:07
94
SVD (Singular Value Decomposition) Intuition
12:12
95
LSA / LSI: Applying SVD to NLP
07:47
96
Latent Semantic Analysis / Latent Semantic Indexing in Python
09:16
97
LSA / LSI Exercises
06:01
98
Deep Learning Introduction (Intermediate-Advanced)
04:58
99
The Neuron - Section Introduction
02:21
100
Fitting a Line
14:24
101
Classification Code Preparation
07:21
102
Text Classification in Tensorflow
12:10
103
The Neuron
09:59
104
How does a model learn?
10:54
105
The Neuron - Section Summary
01:52
106
ANN - Section Introduction
07:00
107
Forward Propagation
09:41
108
The Geometrical Picture
09:44
109
Activation Functions
17:19
110
Multiclass Classification
08:42
111
ANN Code Preparation
04:36
112
Text Classification ANN in Tensorflow
05:44
113
Text Preprocessing Code Preparation
11:34
114
Text Preprocessing in Tensorflow
05:31
115
Embeddings
10:14
116
CBOW (Advanced)
04:08
117
CBOW Exercise Prompt
00:58
118
CBOW in Tensorflow (Advanced)
19:25
119
ANN - Section Summary
01:33
120
Aside: How to Choose Hyperparameters (Optional)
06:22
121
CNN - Section Introduction
04:35
122
What is Convolution?
16:39
123
What is Convolution? (Pattern Matching)
05:57
124
What is Convolution? (Weight Sharing)
06:42
125
Convolution on Color Images
15:59
126
CNN Architecture
20:59
127
CNNs for Text
08:08
128
Convolutional Neural Network for NLP in Tensorflow
05:32
129
CNN - Section Summary
01:28
130
RNN - Section Introduction
04:47
131
Simple RNN / Elman Unit (pt 1)
09:21
132
Simple RNN / Elman Unit (pt 2)
09:43
133
RNN Code Preparation
09:46
134
RNNs: Paying Attention to Shapes
08:27
135
GRU and LSTM (pt 1)
17:36
136
GRU and LSTM (pt 2)
11:37
137
RNN for Text Classification in Tensorflow
05:57
138
Parts-of-Speech (POS) Tagging in Tensorflow
19:51
139
Named Entity Recognition (NER) in Tensorflow
05:14
140
Exercise: Return to CNNs (Advanced)
03:20
141
RNN - Section Summary
01:59
142
Anaconda Environment Setup
20:21
143
How to install Numpy, Scipy, Matplotlib, Pandas, IPython, Theano, and TensorFlow
17:15
144
How to Code by Yourself (part 1)
15:55
145
How to Code by Yourself (part 2)
09:24
146
Proof that using Jupyter Notebook is the same as not using it
12:30
147
How to Succeed in this Course (Long Version)
10:25
148
Is this for Beginners or Experts? Academic or Practical? Fast or slow-paced?
22:05
149
Machine Learning and AI Prerequisite Roadmap (pt 1)
11:19
150
Machine Learning and AI Prerequisite Roadmap (pt 2)
16:08
151
What is the Appendix?
02:49
152
BONUS
05:32
Unlock unlimited learning

Get instant access to all 151 lessons in this course, plus thousands of other premium courses. One subscription, unlimited knowledge.

Learn more about subscription

Related courses

Frequently asked questions

What prerequisites are needed for this course?
The course is designed for students at all levels, including beginners, intermediates, and advanced learners, as noted in the lesson 'Are You Beginner, Intermediate, or Advanced? All are OK!'. However, familiarity with Python and a basic understanding of machine learning concepts will be beneficial for following the course content more effectively.
What kind of projects will I build during the course?
Students will engage in various hands-on projects, such as building a text classifier using probability models, a language model with Markov models, and an article spinner using N-Gram approaches. These projects are designed to reinforce the theoretical concepts covered in lessons like 'Building a Text Classifier' and 'Article Spinner in Python'.
Who is the target audience for this course?
This course is ideal for individuals interested in applying machine learning and natural language processing techniques within Python. It caters to data scientists, software engineers, and researchers looking to enhance their skills in text analysis and language modeling. The course material, including topics like neural word embeddings and Markov models, supports a wide range of professional applications.
What tools and libraries are covered in the course?
The course covers several tools and libraries essential for natural language processing in Python. Key libraries include NLTK for text preprocessing and vector models, and frameworks for neural embeddings like word2vec and GloVe. Students will also learn about probabilistic models and their implementation in Python.
What topics are not covered in the course?
While the course offers a comprehensive overview of text preprocessing and probabilistic models, it does not delve into advanced deep learning models like Transformers in detail. It provides the foundational knowledge needed to understand models such as BERT and GPT-3 but does not cover them extensively.
How much time will I need to commit to complete this course?
The course consists of 152 lessons, each varying in length, but the total runtime is not explicitly stated. Students should be prepared to invest a significant amount of time in understanding theoretical concepts and completing coding exercises and projects. Regular practice and review of the material are recommended for mastery.
How does this course help in advancing my career in data science?
By covering essential aspects of natural language processing and machine learning, the course equips students with skills applicable to various data science roles. Understanding vector models, text classification, and probability models enhances one's ability to tackle complex text-based challenges in fields such as finance, bioinformatics, and AI research.