Natural Language Processing With Cutting Edge Models

Natural Language Processing With Cutting Edge Models
Published 10/2024
MP4 | Video: h264, 1920x1080 | Audio: AAC, 44.1 KHz
Language: English | Size: 9.62 GB | Duration: 27h 6m

NLP : NLTK, Machine and Deep Learning for NLP, Word Embeddings, Markov Model, Transformers, Generative AI for text

What you'll learn

Text Preprocessing and Text Vectorization

Machine Learning Methods for Text Classification

Neural Networks for Text Classification

Sentiment Analysis and Spam Detection

Topic Modeling

Word Embeddings and Neural Word Embeddings

Word2Vec and GloVe

Generative AI for Text data

Markov Models for Text Generation

Recurrent Neural Networks and LSTM

Seq2Seq Networks for Text Generation

Machine Translation

Transformers

Requirements

Some Python Programming Knowledge

Some knowledge about machine learning is preferred

Description

Hi everyone,This is a massive 3-in-1 course covering the following:1. Text Preprocessing and Text Vectorization2. Machine Learning and Statistical Methods3. Deep Learning for NLP and Generative AI for text.This course covers all the aspects of performing different Natural Language processing using Machine Learning Models, Statistical Models and State of the art Deep Learning Models such as LSTM and Transformers.This course will set the foundation for learning the most recent and groundbreaking topics in AI related Natural processing tasks such as Large Language Models, Diffusion models etc.This course includes the practical oriented explanations for all Natural Language Processing tasks with implementation in PythonSections of the Course· Introduction of the Course· Introduction to Google Colab· Introduction to Natural Language Processing· Text Preprocessing· Text Vectorization· Text Classification with Machine Learning Models· Sentiment Analysis· Spam Detection· Dirichlet Distribution· Topic Modeling· Neural Networks· Neural Networks for Text Classification· Word Embeddings· Neural Word Embeddings· Generative AI for NLP· Markov Model for Text Generation· Recurrent Neural Networks ( RNN )· Sequence to sequence (Seq2Seq) Networks . Seq2Seq Networks for Text Generation. Seq2Seq Networks for Language Translation· Transformers· Bidirectional LSTM· Python RefresherWho this course is for:· Students enrolled in Natural Language processing course.· Beginners who want to learn Natural Language Processing from fundamentals to advanced level· Researchers in Artificial Intelligence and Natural Language Processing.· Students and Researchers who want to develop Python Programming skills while solving different NLP tasks.· Want to switch from Matlab and Other Programming Languages to Python.

Overview

Section 1: Introduction to course and course material

Lecture 1 Introduction of the course

Lecture 2 Course Material

Lecture 3 How to succeed in this course

Section 2: Introduction to Google Colab

Lecture 4 Introduction of the section

Lecture 5 Mounting the drive and reading Dataset

Lecture 6 Reading and displaying images

Lecture 7 Reading More Datasets

Lecture 8 Uploading Course Material to Google drive

Section 3: Introduction to Natural Language Processing ( NLP )

Lecture 9 Introduction to NLP

Lecture 10 NLP History

Lecture 11 Applications of NLP

Lecture 12 Vocabulary and Corpus

Section 4: Text Preprocessing

Lecture 13 Introduction of the section

Lecture 14 Tokenization and Challenges

Lecture 15 Types of Tokenization

Lecture 16 Project01 : Tokenization with Python

Lecture 17 Project02 : Tokenization with NLTK

Lecture 18 Stemming, Lemmatization and Stopwords

Lecture 19 Stemming and Lemmatization with NLTK

Section 5: Text Vectorization

Lecture 20 Introduction of the section

Lecture 21 Word to Index Mapping

Lecture 22 Word to Index Mapping with Python

Lecture 23 Bag of Words

Lecture 24 Count Vectorizer

Lecture 25 Count Vectorizer with Python

Lecture 26 Machine Learning with Count Vectorizer

Lecture 27 TF-IDF Vectorizer

Lecture 28 TF-IDF Vectorizer in Python

Section 6: Text Classification with Machine Learning Models

Lecture 29 Introduction of the section

Section 7: Sentiment Analysis

Lecture 30 Introduction of the section

Lecture 31 Basic Concept of Logistic Regression

Lecture 32 Limitations of Regression

Lecture 33 Transforming Linear Regression into Logistic Regression

Lecture 34 Model Evaluation

Lecture 35 Accuracy-Precision-Recall-F1 score

Lecture 36 Project01 : Sentiment Analysis by Logistic Regression

Lecture 37 Intuition behind K-Nearest Neighbor ( KNN )

Lecture 38 KNN Algorithm

Lecture 39 Numerical Example on KNN

Lecture 40 Project02 : Sentiment Analysis With KNN

Lecture 41 Pre-trained Sentiment Analysis Model

Section 8: Spam Detection

Lecture 42 Introduction of the section

Lecture 43 Fundamentals of Probability

Lecture 44 Conditional Probability and Bayes Theorem

Lecture 45 Numerical on Bayes Theorem

Lecture 46 Naive Bayes Classification

Lecture 47 Comparing Naive Bayes Classification with Logistic Regression

Lecture 48 Project01 : Spam detection with Naive Bayes Classifier

Lecture 49 Fundamentals of Support Vector Machine ( SVM )

Lecture 50 Mathematics of SVM

Lecture 51 Hard and Soft Margin Classifier

Lecture 52 Decision rule for SVM

Lecture 53 Kernel trick in SVM

Lecture 54 Spam detection with SVM

Section 9: Dirichlet Distribution ( Optional )

Lecture 55 Introduction of the section

Lecture 56 Data Distribution in Statistics

Lecture 57 Dirichlet Distribution

Lecture 58 Applications of Dirichlet Distribution

Section 10: Topic Modeling

Lecture 59 Introduction of the section

Lecture 60 Topic Modeling

Lecture 61 Latent Dirichlet Allocation ( LDA )

Lecture 62 Project01 : Topic Modeling with LDA

Lecture 63 Non Negative Matrix Factorization ( NMF )

Lecture 64 Topic Modeling with NMF

Section 11: Neural Networks

Lecture 65 Introduction of the section

Lecture 66 The Perceptron

Lecture 67 Features, Weight and Activation Functions

Lecture 68 Learning of Neural Network

Lecture 69 Need of Activation Functions

Lecture 70 Adding Activation Function to Neural Network

Lecture 71 Sigmoid as an Activation Function

Lecture 72 Hyperbolic Tangent Function

Lecture 73 ReLU and Leaky ReLU

Lecture 74 MSE Loss Function

Lecture 75 Cross Entropy Loss Function

Lecture 76 Softmax Function

Section 12: Neural Network for Text Classification

Lecture 77 Introduction of the section

Lecture 78 Code Preparation

Lecture 79 Project01 : Implementing Neural Network in TensorFlow Part-01

Lecture 80 Project01 : Implementing Neural Network in TensorFlow Part-02

Lecture 81 Project02 : Text Classification with Neural Network Part-01

Lecture 82 Project02 : Text Classification with Neural Network Part-02

Section 13: Word Embeddings ( Statistical Method )

Lecture 83 Introduction of the section

Lecture 84 One Hot Encoding

Lecture 85 One Hot Encoding in Python

Lecture 86 Co-occurrence Matrix - Word Embeddings Intuition

Section 14: Neural Word Embeddings ( Word2Vec )

Lecture 87 Introduction of the section

Lecture 88 Methods of Word Embeddings

Lecture 89 Implementing Methods of Word2Vec

Lecture 90 Continuous Bag of Words ( CBOW )

Lecture 91 Project01 : Implementing CBOW Part-01

Lecture 92 Project01 : Implementing CBOW Part-02

Lecture 93 Project01 : Implementing CBOW Part-03

Lecture 94 Project02 : Implementing CBOW using Large Corpus

Lecture 95 Pretrained Word2Vec

Lecture 96 Project03 : Find Analogies with Word2Vec

Lecture 97 Text Classification using Word2Vec

Section 15: Neural Word Embeddings ( GloVe )

Lecture 98 Introduction of the section

Lecture 99 Project01 : GloVe Implementation

Lecture 100 Project02: Pretrained GloVe

Lecture 101 Project03 : Text Classification using GloVe

Section 16: Generative AI for NLP

Lecture 102 Introduction of the section

Section 17: Markov Model for Text Generation

Lecture 103 Introduction of the section

Lecture 104 Markov Model and State Transition Matrix

Lecture 105 Project01 : Text Generation by State Transition Matrix

Lecture 106 First Order Markov Model for Text Generation

Lecture 107 Project02 : Text Generation by First Order Markov Model

Lecture 108 Second Order Markov Model

Lecture 109 Project03 : Text Generation by Second Order Markov Model

Lecture 110 Project04 : Text Generation by Second Order Markov Model using Large Corpus

Lecture 111 Project05 : Text Generation by Third Order Markov Model

Section 18: Recurrent Neural Networks ( RNN )

Lecture 112 Introduction of the section

Lecture 113 Need of RNN

Lecture 114 Sequential Data

Lecture 115 ANN to RNN

Lecture 116 Back Propagation Through Time

Lecture 117 Long Short Term Memory ( LSTM )

Lecture 118 LSTM Gates

Lecture 119 Concept of Batch size, Sequence length and Feature dimension

Lecture 120 Project01: LSTM Shapes

Lecture 121 Project02 : Time Series Prediction by LSTM

Lecture 122 MNIST Classification by LSTM

Lecture 123 Project03: MNIST Classification Part01

Lecture 124 Project03: MNIST Classification Part02

Lecture 125 Text Classification

Lecture 126 Project04 : Text Preprocessing

Lecture 127 Project05 : Text Classification by LSTM

Section 19: Sequence to sequence ( Seq2Seq ) Network

Lecture 128 Introduction of the section

Lecture 129 Implementing Seq2Seq Network and Teacher Forcing

Lecture 130 Project01 : Text Generation by Seq2Seq Network

Lecture 131 Project02 : Machine Translation ( Language Translation ) by Seq2Seq Network

Section 20: Transfer Learning with Transformer

Lecture 132 Introduction of the section

Lecture 133 Project01 : Sentiment Analysis

Lecture 134 Project02 : Text Generation

Lecture 135 Project03 : Masked Language Modeling

Lecture 136 Project04 : Text Summarization

Lecture 137 Project05 : Machine Translation

Lecture 138 Project06 : Question Answering

Section 21: Transformer Architecture

Lecture 139 Fundamental Building Blocks of Transformer

Lecture 140 Encoder and Decoder

Lecture 141 Positional Encoding

Lecture 142 Attention Mechanism

Section 22: Fine Tuning the Transformer

Lecture 143 Introduction of the section

Lecture 144 Project01 : Model and Tokenization

Lecture 145 Project02 : Fine Tuning Transformer for Sentiment Analysis

Lecture 146 Project03 : Fine Tuning Transformer on Custom Dataset

Section 23: More Sections

Lecture 147 Introduction of the section

Section 24: Bidirectional LSTM

Lecture 148 Introduction of the section

Lecture 149 Working of Bidirectional LSTM

Lecture 150 Project01 : Shapes of Bidirectional LSTM

Lecture 151 Project02 : Bidirectional LSTM for MNIST dataset

Lecture 152 Dual Bidirectional LSTM

Lecture 153 Project03 : Dual Bidirectional LSTM for MNIST dataset

Section 25: Time Series Transformer

Lecture 154 Introduction of the section

Lecture 155 Project01 : Shapes of Encoder

Lecture 156 Project02 : Time Series Classification

Lecture 157 Project03 : Time Series Transformer Shapes

Lecture 158 Project04 : Time Series Reconstruction by Time Series Transformer

Section 26: Python Refresher

Lecture 159 Introduction of the section

Lecture 160 Arithmetic with Python

Lecture 161 Comparison and Logical Operations

Lecture 162 Conditional Statements

Lecture 163 NumPy Arrays Part01

Lecture 164 NumPy Arrays Part02

Lecture 165 NumPy Arrays Part03

Lecture 166 Plotting and Visualization Part01

Lecture 167 Plotting and Visualization Part02

Lecture 168 Plotting and Visualization Part03

Lecture 169 Plotting and Visualization Part04

Lecture 170 Lists in Python

Lecture 171 For Loops Part01

Lecture 172 For Loops Part02

Lecture 173 While Loop

Lecture 174 Strings in Python

Lecture 175 Print Formatting with Strings

Lecture 176 Dictionaries Part01

Lecture 177 Dictionaries Part02

Lecture 178 Seaborn part01

Lecture 179 Seaborn part02

Lecture 180 Seaborn part03

Lecture 181 Pandas Part01

Lecture 182 Pandas Part02

Lecture 183 Pandas Part03

Lecture 184 Pandas Part04

Lecture 185 Functions in Python Part01

Lecture 186 Functions in Python Part02

Lecture 187 Classes in Python

Lecture 188 Tuples

Lecture 189 Lambda Function

Lecture 190 Map Function

Lecture 191 Reduce Function

Lecture 192 Filter function

Lecture 193 zip function

Lecture 194 join function

Section 27: Bonus Lecture

Lecture 195 Introduction of the section

Students enrolled in Natural Language processing course.,Beginners who want to learn Natural Language Processing from fundamentals to advanced level,Researchers in Artificial Intelligence and Natural Language Processing.,Students and Researchers who want to develop Python Programming skills while solving different NLP tasks.,Want to switch from Matlab and Other Programming Languages to Python