This course is part of specialization programs

This course can be applied to multiple Specializations or Professional programs. Completing this course will count towards your learning in any of the following programs

• Deep Learning A-Z Course
• Artificial Intelligence A-Z Course

Pre-skills/ Prerequisites

A learner must have completed Deep Learning Basic Course

Course Curriculum

Module 1 – Text and Speech preprocessing – 6 Hours

• Working with speech to text and text to speech conversions
• Text pre processing with Regular Expressions
• Working with NLTK
• Tokenization, stemming, lemmatization
• PoS Tagging
• Spelling correction
• Working with spaCy
• NER
• Dependency Parsing
• Document Similarity Matching

Module 2 – Text Classification – 6 Hours

• Text Classification – Vectorization Techniques
• Tf-IDF, count vector co-occurence Vectorization
• N-gram feature modelling
• Feature Pruning methods
• Project: Sentiment Analysis
• Project: Building an Email Classification Model

Module 3 – Social Media Analytics – 4 Hours

• Collecting live tweets from twitter
• Cleaning and processing tweets
• Information extraction from tweets
• Converting unstructured data to semi structured
• Analysing tweet data
• Project: Streaming live tweets and Sentiment Analysis
• Wordcloud

Module 4 – RNN and LSTM – 8 Hours

• Recurrent Neural Networks
• Basic concepts of RNN
• Unfolding Recurrent Neural Networks
• The Vanishing Gradient Problem
• The Exploding Gradient Problem
• LSTM Networks
• Understanding of LSTM
• Erase Gate, Input Gate and Read Gate
• Overview of GRU
• Case study
• Implementing LSTM using Tensorflow-keras
• implementing LSTM using Pytorch
• Text Classification using NLP
• Developing a chatbot application using NLP

Module 5 – Transfer Learning for NLP – 8 Hours

• Understanding the concept of Transfer Learning for NLP
• General issues with NLP problems
• Ideas for transfer learning approach for different situations in case of NLP
• Using Universal Sentence Encoders
• Deep Averaging Networks
• Sequence to Sequence Models
• Encoder and Decoder Understanding
• Attention-based models
• Transformer Models – Self Attention models
• Using ELMo for word vectorization
• Working of BERT
• Working of GPT-2
• Working of XLNet
• Using BERT, GPT-2, XLNet for text classification

Module 6 – Capstone Project

• Working Final Project
• Splitting final Project into phases
• Working on structuring project
• Summary

Course Features

• More than 80% hands-on session
• Project-oriented learning
• Cloud-based LMS
• Experienced Trainer
• Masterclass for Expert
• Standard reading materials
• Study resources
• Graded Quizzes
• Real-time case study-based projects
• Discussion Forum

Machine Requirement

1. Windows Machine (Windows 7 or Above) /Linux Machine
2. Only 64 Bit
3. 8 GB RAM 
4. NVIDIA Graphics Card (Recommended)

Ask for one to one online meeting with our technical expert.

—————-