NATURAL LANGUAGE PROCESSING

Do you get annoyed by the constant spams in your mail box? Wouldn’t it be nice if we had a program to check your spellings? In this module learn how to build a spell checker & spam detector using techniques like phonetic hashing, bag-of-words, TF-IDF, etc.

• Introduction to NLP
• Basic Lexical Processing
• Advanced Lexical Processing

SYNTACTIC PROCESSING

Learn how to analyze the syntax or the grammatical structure of sentences with the help of algorithms & techniques like HMMs, Viterbi Algorithm, Named Entity Recognition (NER), etc.

• Introduction to Syntactic Processing
• Parsing
• Information Extraction
• Conditional Random Fields

SYNTACTIC PROCESSING -ASSIGNMENT

Build a POS tagger for tagging unknown words using HMMs and modified Viterbi algorithm

• Problem Statement
• Evaluation
• Rubric
• Final Submission
• Solution

SEMANTIC PROCESSING

Learn the most interesting area in the field of NLP and understand different techniques like word-embeddings, LSA, topic modeling to build an application that extracts opinions about socially relevant issues (such as demonetization) on social media platforms.

• Introduction to Semantic Processing
• Distributional Semantics Topic Modelling
• Social Media Opinion Mining
• Semantic Processing
• Case Study

BUILDING CHATBOTS WITH RASA

Imagine if you could make restaurant booking without opening Zomato. Build your own restaurant-search chatbot with the help of RASA - an open source framework and deploy it on Slack.

• Problem Statement
• Evaluation
• Rubric
• Final Submission
• Solution

DEEP LEARNING

Learn the most sophisticated and cutting-edge technique in machine learning - Artificial Neural Networks or ANNs.

• Structure of Neural Networks
• Feed Forward in Neural Networks
• Backpropagation in Neural Networks
• Modifications to Neural Networks
• Hyperparameter Tuning in Neural Networks

NEURAL NETWORKS - ASSIGNMENT

Build a neural network from scratch in Numpy to identify the type of skin cancer from images.

• Problem Statement
• Evaluation
• Rubric
• Final Submission
• Solution

CONVOLUTIONAL NEURAL NETWORKS -INDUSTRY APPLICATIONS

Learn the basics of CNN and OpenCV and apply it to Computer Vision tasks like detecting anomalies in chest X-Ray scans, vehicle detection to count and categorise them to help the government ascertain the width and strength of the road.

• Building CNNs with Python and Keras
• CNN Architectures and Transfer Learing
• Style Transfer and Object Detection Industry
• Demo:Using CNNs with Flowers Images Industry
• Demo:Using CNNs with X-ray Images

Azure Machine Learning

CREATE MACHINE LEARNING MODELS

• Explore and analyze data with Python
• Train and evaluate machine learning models
• Train and evaluate regression models
• Train and evaluate classification models
• Train and evaluate clustering models
• Train and evaluate deep learning models

CREATE NO-CODE PREDICTIVE MODELS WITH AZURE MACHINE LEARNING

• Use Automated machine learning in Azure Machine Learning
• Creating a regression model with Azure Machine Learning designer
• Creating a classification model with Azure Machine Learning designer
• Creating a clustering model with Azure Machine Learning designer

BUILD AI SOLUTIONS WITH AZURE MACHINE LEARNING

• Introduction to Azure machine learning SDK
• Train a machine learning model with Azure Machine Learning
• Work with Data in Azure Machine Learning
• Work with Compute in Azure Machine Learning
• Orchestrate machine learning with pipelines
• Deploy real-time machine learning services with Azure Machine Learning
• Deploy batch inference pipelines with Azure Machine Learning
• Tune hyper parameters with Azure Machine Learning
• Automate machine learning model selection with Azure Machine Learning
• Explore differential privacy
• Explain machine learning models with azure machine learning
• Detect and mitigate unfairness in models with azure machine learning
• Monitor models with azure machine learning
• Monitor data drift with azure machine learning.

Big Data Technologies

Big Data - Beyond The Hype, Big Data Skills And Sources Of Big Data, Big Data Adoption, Research And Changing Nature Of Data Repositories, Data Sharing And Reuse Practices And Their Implications For Repository Data Curation, Overlooked And Overrated Data Sharing, Data Curation Services In Action, Open Exit: Reaching The End Of The Data Life Cycle, The Current State Of Meta-Repositories For Data, Curation Of Scientific Data At Risk Of Loss: Data Rescue And Dissemination

Hadoop:

Introduction of Big data programming-Hadoop, The ecosystem and stack, The Hadoop Distributed File System (HDFS), Components of Hadoop, Design of HDFS, Java interfaces to HDFS, Architecture overview, Development Environment, Hadoop distribution and basic commands, Eclipse development, The HDFS command line and web interfaces, The HDFS Java API (lab), Analyzing the Data with Hadoop, Scaling Out, Hadoop event stream processing, complex event processing, MapReduce Introduction, Developing a Map Reduce Application, How Map Reduce Works, The MapReduce Anatomy of a Map Reduce Job run, Failures, Job Scheduling, Shuffle and Sort, Task execution, Map Reduce Types and Formats, Map Reduce Features, Real-World MapReduce,

Hadoop Environment:

Setting up a Hadoop Cluster, Cluster specification, Cluster Setup and Installation, Hadoop Configuration, Security in Hadoop, Administering Hadoop, HDFS – Monitoring & Maintenance, Hadoop benchmarks,

Introduction to HIVE,

Programming with Hive: Data warehouse system for Hadoop, Optimizing with Combiners and Practitioners (lab), Bucketing, more common algorithms: sorting, indexing and searching (lab), Relational manipulation: map-side and reduce-side joins (lab), evolution, purpose and use, Case Studies on Ingestion and warehousing

HBase:

Overview, comparison and architecture, java client API, CRUD operations and security

Apache Spark APIs for large-scale data processing:

Overview, Linking with Spark, Initializing Spark, Resilient Distributed Datasets (RDDs), External Datasets, RDD Operations, Passing Functions to Spark, Job optimization, Working with Key-Value Pairs, Shuffle operations, RDD Persistence, Removing Data, Shared Variables, EDA using PySpark, Deploying to a Cluster Spark Streaming, Spark MLlib and ML APIs, Spark Data Frames/Spark SQL, Integration of Spark and Kafka, Setting up Kafka Producer and Consumer, Kafka Connect API, Mapreduce, Connecting DB’s with Spark

Tableau for Data Visualization

Data warehousing Concepts

Understand how to formulate and validate hypotheses for a population to solve real-life business problems.

• What is DWH?
• Characteristics of Datawarehouse
• Difference between OLTP and DWH
• Architecture of DWH
• Various BI tools
• Types of DWH
• Types of Dimensional Data Modeling
• Surrogate key
• Types of Dimension

Tableau Desktop (Introduction)

• Introduction Tableau
• Connecting to Excel, CSV Text Files
• Getting Started
• Product Overview
• Connecting to Databases
• Working with Data
• Analyzing
• Formatting
• Introduction to Calculations
• Dashboard Development
• Sharing
• Data Calculations
• Aggregate Calculations
• User Calculations
• Table Calculations
• Logical Calculations
• String Calculations
• Number Calculations
• Type Conversion
• Parameters
• Filtering Conditions
• Filtering Measures
• Histograms
• Sorting
• Grouping
• Sets
• Tree maps, word clouds and bubble charts
• Pareto Charts
• Waterfall Charts
• Bump Charts
• Funnel Charts
• Bollinger Bands