AI & Data Science from iHub, IIT Roorkee - Prime

Data Handling with NumPy:

• NumPy Arrays, CRUD Operations, etc.
• Linear Algebra – Matrix multiplication, CRUD operations, Inverse, Transpose, Rank, Determinant of a matrix, Scalars, Vectors, Matrices.

Data Manipulation Using Pandas:

• Loading the data, dataframes, series, CRUD operations, splitting the data, etc.

Data Preprocessing:

• Exploratory Data Analysis, Feature engineering, Feature scaling, Normalization, standardization, etc.
• Null Value Imputations, Outliers Analysis and Handling, VIF, Bias-variance trade-off, cross validation techniques, train-test split, etc.
• Data Visualization: Bar charts, scatter plots, count plots, line plots, pie charts, donut charts, etc. with Python matplotlib. Regression plots, categorical plots, area plots, etc, with Python seaborn.

SQL Basics:

Fundamentals of RDBMS & SQL, ACID properties, Normalization, understanding of SQL Tables, Joins and Variables

Advanced SQL:

• SQL Functions, Subqueries, Rules, Views
• Nested Queries, string functions, pattern matching, Mathematical functions, Date-time functions, etc.
• Deep Dive into User Defined Functions, Types of UDFs, Inline table value, multi-statement table.
• Stored Procedures, Rank Function, SQL ROLLUP, etc.
• SQL Optimization and Performance
• Record grouping, searching, sorting, etc.
• Indexing – Clustered Indexes, Common Table Expressions

• American Sign Language Recognition

Train custom models using pre-trained ones to identify American Sign Language gestures.

• Gesture Recognition

Use pre-trained models for real-time gesture recognition with deep learning and Computer vision techniques.

• Shark Species Classification

Use deep learning library like TensorFlow for image classification to identify the shark species.

• Stock Market Forecasting

Forecast the stock market trends and prices with historical data using deep learning techniques like LSTM.

• Cyber Threat Detection Using NLP

Applying Natural Language Processing and deep learning techniques in detecting cybersecurity threats.

• Introduction to AI & Data Science, CNN & RNN
• Introduction to Keras API, Tensorflow and Neural Networks
• Single Cell (perceptron)
• Multi cell perceptron Topology, gradient-descent, Back-propagation
• Weights & Biases
• Build a Neural Network from scratch
• Use cases of Deep Learning in the industry
• Difference between Data Science, Machine Learning, Deep Learning & AI & Data Science
• Lifecycle of Deep Learning Project

• NLP: Learn how to make computers understand, interpret, and generate human language.
• Text Pre-processing: Tokenization, stemming, lemmatization, N-grams, and entity recognition.
• Text Classification: Sentiment analysis, Naive Bayes, Count Vectorizer, and TF-IDF.
• Language Modeling: Sequence tagging, syntax trees, and automatic paraphrasing.
• AI Applications: Building chatbots and recommendation engines using NLP.
• Computer Vision: Constructing CNNs with TensorFlow, object detection, and image filtering.
• Deep Learning: Generating images with neural style, deep generative models.

• LSTM: What is LSTM? How does LSTM work, Applications of LSTM, etc.
• Transformers: What are transformers, how does a transformer work in deep learning, applications of transformers, types of transformers, encoder-decoded, self-attention, etc.
• BERT: Language Models, what is BERT, how does BERT work, how is BERT different from LSTM, applications of BERT, etc.
• GPT: What are generative pre-trained models (GPT), how does a GPT work? Real-life examples of GPT, etc.
• LLM: NLP and Language models, what are LLMs, how does an LLM work, applications of LLM, etc.
• VAEs: Introduction to Variational Autoencoders, Architecture of VAEs, creating VAEs for image generation.
• LangChain: Intuition for LangChain, LangChain applications, LangChain architecture, how to work with LangChains, etc.

• Prompt Engineering: Science behind Prompts, Prompt Engineering Basics, Impact and usage of Prompt Engineering, Prompt Engineering tools, Effectiveness of Prompts, etc.
• Image-Based Applications of Generative AI: Image-based workflows and artifacts using Generative AI with image generation, text-image generation, etc.
• Text-Based Applications of Generative AI: Leveraging Text summarization and text generation for text-based applications using Generative AI tools.
• Audio-Based Applications of Generative AI: Text to Audio generation, Audio processing, Audio generation leveraging Generative AI tools to create end-to-end applications.

• Agentic AI Foundations and System Architecture
• Agent Components – Memory, Tools, and RAG
• Agent Development and Use Cases
• Agent Deployment