Duration
3 days
What you'll learn
- Understand the importance, principles, and fields of AI and ML,NLP and DL
- Learn how can clean your data and prepare it for analysis
- Apply Supervised and Unsupervised Learning Machine Learning algorithms to real-world problems
- Learn how can you apply Artificial Intelligence and Machine Learning in your areas of functions to do predictions
- Understand the various concepts of natural language processing along with their implementation
- Build natural language processing based applications
- Learn about the different modules available in PythonforNLP
- Create personal text summarizer
Day 1
9:00am-10:30am
Introduction
- Artificial Intelligence (AI) Overview
- What is Machine Learning (ML)?
- AI vs ML vs Data Science
- Relationship between Deep Learning (DL) and Machine Learning
- Tools/Platforms for ML, DL and AI
- Machine Learning Project End to End Pipeline
- How we can define a business problem
10:30am-10:45pm Morning Break
10:45pm-12:30pm
Data Cleaning and Feature Engineering
- What is Feature Engineering?
- Why Feature Engineering?
- How to apply Feature Engineering?
- Discussions on various scenarios
- Data Cleaning & Wrangling using Pandas
- Missing Values and Outlier
12:30pm-1:30pm Lunch
1:30pm-3:30pm
Machine Learning using Scikit Learn
- Types of Machine Learning
- Key Algorithms in Machine Learning
- Practical Applications of Machine Learning
- Various frameworks/Libraries popular for ML
- Concepts and Terms
- Why Scikit Learn?
3:30pm-3:45pm Afternoon Break
3:45pm-5:00pm
Supervised Machine Learning
- Key Classification Algorithms
- Naïve Bayes Classifier
- D-tree and Random Forest Classifier
- SVM Classifier
- Confusion Matrix
- Accuracy
- Key Regression Algorithms
- Linear, Logistic Regressions
- Gradient Descent
- Loss function
- Bias vs Variance Trade off
- Evaluating Models
Day 2
9:00am-10:30am
Un-Supervised Machine Learning
- Why Un-supervised learning is important?
- Where it can be applied?
- Principal Component Analysis (PCA)
- Performing Clustering of data
10:30am-10:45pm Morning Break
10:45pm-12:30pm
Introduction to Deep Learning
- Introduction to Machine Learning?
- What is Deep Learning?
- Relationship between Deep Learning and Machine Learning
- Deep Learning Use cases
- Concepts and Terms
- How to implement Deep Learning?
- Various Libraries, Pros & Cons
12:30pm-1:30pm Lunch
1:30pm-3:30pm
Artificial Neural Network
- Introduction to Neural Networks
- The Neuron
- Introduction to Perceptron
- The Activation Function
- Neural Network Activation Functions
- Basic Neural Nets
- Concepts
- Gradient Descent
- Stochastic Gradient Descent
3:30pm-3:45pm Afternoon Break
3:45pm-5:00pm
TensorFlow
- What is TensorFlow?
- Installing TensorFlow
- TensorFlow Graphs
- Variables and Placeholders
- Activation Functions
Day 3
9:00am-10:30am
Recurrent Neural Networks (RNN) and Convolutional Neural Networks (CNN)
- CNN History
- Understanding CNNs
- CNN Application
- Introduction to Optimization
- Hyperparameter tuning
- Regularization
- Recurrent Neural Networks (RNNs)
- Application of RNNs
10:30am-10:45pm Morning Break
10:45pm-12:30pm
Modern Architecture
- Understand modern architectures of RNNs: LSTM, GRU
Introduction to NLP
- What is NLP?
- Installing Anaconda Python
12:30pm-1:30pm Lunch
1:30pm-3:30pm
Regular Expressions
- Introduction to Regular Expressions
- Finding Patterns in Text
- Substituting Patterns in Text
- Shorthand Character Classes
- Character Ranges - Text
- Preprocessing using Regex
NLP Core
- Installing NLTK in Python
- Tokenizing Words and Sentences
- How tokenization works?
- Introduction to Stemming and Lemmatization
- Stemming using NLTK
- Lemmatization using NLTK
- Stop word removal using NLTK
- Parts Of Speech Tagging
- POS Tag Meanings
- Named Entity Recognition
- Text Modelling using Bag of Words Model
- Building the BOW Model
- Text Modelling using TF-IDF Model
- Understanding the N-Gram Model
- Understanding Latent Semantic Analysis
- Word Synonyms and Antonyms using NLTK
- Word Negation Tracking in Python
3:30pm-3:45pm Afternoon Break
3:45pm-5:00pm
Project 1 - Text Classification
- Getting the data for Text Classification
- Importing the dataset
- Persisting the dataset
- Preprocessing the data
- Transforming data into BOW Model
- Transform BOW model into TF-IDF Model
- Creating training and test set
- Understanding Logistic Regression
- Training our classifier
- Testing Model performance
- Saving our Model
- Importing and using our Model
Project 2 - Twitter Sentiment Analysis
- Setting up Twitter Application
- Initializing Tokens
- Client Authentication
- Fetching real time tweets
- Loading TF-IDF Model and Classifier
- Preprocessing the tweets
- Predicting sentiments of tweets
- Plotting the results
Project 3 - Text Summarization using web page data
- Understanding Text Summarization
- Fetching article data from the web
- Parsing the data using Beautiful Soup
- Preprocessing the data
- Tokenizing Article into sentences
- Building the histogram
- Calculating the sentence scores
- Getting the summary
Word2Vec Analysis
- Understanding Word Vectors
- Importing the data
- Preparing the data
- Training the Word2Vec Model
- Testing Model Performance
- Improving the Model
- Exploring Pre-trained Models
Programme scope, delivery arrangements and suitability are confirmed during enquiry.