CO1: Apply data processing, exploration, feature extraction, and training and testing of ML models and demonstrate the pivotal role of data in the future of computing.
CO2: Investigate the practical applications of AI in day-to-day businesses and envisage future developments.
CO3: Acquire the skill to use predictive AI models for making data-driven decisions and generative AI models for creative applications, and cultivate a commitment to lifelong learning.
Course Content
Basics of AI & ML
Foundations of AI: AI history, branches of AI, Narrow AI and General AI, Predictive AI and Generative AI, Hardware requirements, Cloud platforms, AI tools. Python for AI and ML: Basics, loops, functions, packages, libraries. Data collection and sources, Data preprocessing, Machine learning workflow. Data-driven emerging technologies. Real world use cases. Data privacy, ethics and societal implications.
Predictive AI
Deeplearning (DL) and predictive modeling, Image feature extraction with CNNs, CNN architectures. CNNs for image classification and image restoration. sequence to sequence models and applications. time series forecasting. DL for dimensionality reduction, segmentation and object detection. Recommendation systems.
Generative AI
Generative models: Autoencoders(AEs), latent space, variational AEs (VAEs), Generative Adversarial Networks (GANs), Conditional GANs, CycleGANs, Attention mechanisms, Multi head attention, Transformer Models: BERT, GPT, Large Language Models (LLMs), Evolution of LLMs.
Real world Use Cases
Machine translation, Text generation with RNNs and GANs, Music composition and generation, Text to speech conversion and voice cloning, Image generation with GANs, Image captioning, style transfer, deepfake, Ethics related to AI generated contents.
Reference:
1.Y. Bengio, I. Goodfellow and A. Courville, Deep Learning, MIT Press, 2016.
2.Francois Chollet, Deep Learning with Python, Manning Publications, 2017
3.Bishop, C., M., Pattern Recognition and Machine Learning, Springer , 2006.
4.Stuart Jonathan Russell, Peter Norvig, Artificial intelligence a modern approach, 4th Edn, Pearson Education, Inc, 2016.
5.David Foster, Generative Deep Learning: Teaching Machines to Paint, Write, Compose, and Play, O'Reilly Media, 2019.
6.Charu C. Aggarwal, Machine Learning for Text, Springer, 2022.