Post Graduate Program in AI and Machine Learning

Python 

• Introduction to Python and IDEs – The basics of the python programming language, how you can use various IDEs for python development like Jupyter, Pycharm, etc. 
• Python Basics – Variables, Data Types, Loops, Conditional Statements, functions, decorators, lambda functions, file handling, exception handling ,etc.
• Object Oriented Programming – Introduction to OOPs concepts like classes, objects, inheritance, abstraction, polymorphism, encapsulation, etc.
• Hands-on Sessions And Assignments for Practice – The culmination of all the above concepts with real-world problem statements for better understanding. 

Linux

• Introduction to Linux  – Establishing the fundamental knowledge of how linux works and how you can begin with Linux OS. 
• Linux Basics – File Handling, data extraction, etc.
• Hands-on Sessions And Assignments for Practice – Strategically curated problem statements for you to start with Linux. 

2.1 Regression Modeling: Logical and Linear
2.2 Classification Modeling: K-nearest neighbor, Naïve Bayes Theorem, and Support Vector Machines (SVM)
2.3 Random forest and decision tree models
2.4 Use of PCA, k-means clustering, and isolated forests for anomaly detection
2.5 Time-series prediction model and recommendation system
2.6 Selection, evaluation, and interpretation of models

Tools covered

3.1 Introduction to neural networking
3.2 Backpropagation
3.3 Stochastic gradient descent
3.4 Deep neural networking and its principles
3.5 CNNs, RNNs, LSTMs, and MLPs
3.6 GANs and Generative deep learning
3.7 Calculus and linear algebra
3.8 TensorFlow, CuPy, Keras, and PyTorch

Tools covered

4.1 Natural Language Processing (NLP) and text mining

• Introduction NLP & text mining
• Applications of text mining
• How NPL works with text mining
• Natural Language Toolkit (NLTK) environment

4.2 Data cleaning and preprocessing

• Various tokenizers and Tokenization
• Frequency distribution
• Stemming, POS tagging, and lemmatization
• Bigrams, Trigrams, and Ngrams
• Entity recognition

4.3 Classification of text

• Overview of Machine Learning
• Words, term frequency, and count vectorize
• Inverse document frequency, text conversion, and confusion matrix
• Naive Bayes Classifier

4.4 Sentence structuring, language modeling, sequence tagging, and sequence tasks

• Language modeling, sequence tagging, and sequence tasks
• Predicting sequence of tags
• Syntax trees
• Context-free grammar
• Chunking
• Automatic paraphrasing of texts

4.5 Vector space models and semantics

• Distributional semantics
• Traditional and topic models
• Tools for sentence and word embeddings

4.6 Dialog systems

• Introduction to task-oriented dialog systems
• Natural language understanding
• Dialog Manager

Tools covered

5.1 Basics of computer vision and OpenCV
5.2 Use of neural networking for image processing
5.3 Classification and clustering of an image using GANs, multitask classifiers, and k-means
5.4 Detection of object
5.5 Image segmentation
5.6 Computer vision trends

6.1 Development of large-scale AI apps using various tools and techniques
6.2 Build and deploy APIs with FastAPI, Swagger, Paperspace, and Postman
6.3 CI/CD pipeline for model production
6.4 Use of TensorFlow Lite, TensorFlow.js, and Streamlit to package model
6.5 Model production using PyTorch, Spark, and PySpark

Tools covered

7.1 Data collection from RSSs, web scraping, and APIs
7.2 Data cleaning and transformation for ML systems
7.3 Automatic transformation tools
7.4 SQL and NoSQL databases to deal with large sets of data
7.5 Spark
7.6 Pandas
7.7 SQL and Spark SQL
7.8 ScrappingHub

Tools covered

Upon completion of the AI and ML course, you can culminate your Machine Learning and AI skills through a real-world industry-based capstone project that aims to make you use all the skills that you have gained in the program.