CO 1: Apply elementary matrix operations, the rank of a matrix, and system of linear
equations (Apply)
CO 2: Discuss the inner product and Gram-Schmidt’s process of orthogonalization
(Discuss)
CO 3: Categorize the concept of probability and random variables (Categorize)
- Introduce students to the foundational concepts and principles of data science.
- Provide an understanding of the data science lifecycle from data collection to interpretation of results.
- Teach the basics of data manipulation, including cleaning, transformation, and preparation.
- Familiarize students with popular programming languages and tools used in data science such as Python, R, and SQL.
- Cover statistical methods and techniques commonly used in data analysis.
- Introduce machine learning concepts and algorithms for predictive modeling and pattern recognition.
- Teach data visualization techniques to effectively communicate findings and insights.
- Explore ethical considerations and best practices in data science, including privacy, bias, and transparency.
- Provide hands-on experience through practical exercises, projects, and case studies.
- Prepare students for further study or careers in data science by building a solid foundation of skills and knowledge.
Course Objective:
To understand the basic theory underlying deep learning and implementing problems that can
be handled by deep learning using Keras.
Course Outcomes:
CO 1: To explore basics of Neural networks and to install and implement Keras.
CO 2: To develop Generative Adversarial Networks using Keras.
CO 3: To implement Word embeddings and understand Recurrent Neural networks.
CO 4: To apply deep learning models for AI Game playing.
MODULE I: Python Fundamentals
MODULE II: Functions
MODULE III: OOP concepts
MODULE IV: Advanced Features