Our career paths help you become job ready faster
35% Off Finance Skills That Get You Hired - Code CFI35
Overview
Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
ABOUT THE COURSE:Natural language processing (NLP) and computer vision (CV) have become increasingly significant due to their wide-ranging applications, such as language translation, speech recognition, image analysis, and automation in the healthcare, education, and transportation sectors. For under graduate and postgraduate college students, this course will offer a strong foundation in the concepts and techniques of deep learning, preparing them for advanced research and enhancing their employability in emerging technologies. Beginners in the industry will also benefit from practical insights into bridging theoretical knowledge with real-world applications, enabling them to contribute effectively to projects involving language and vision-based solutions. Faculty members will gain exposure to the latest developments and tools in the field, supporting their efforts to integrate cutting-edge topics into their teaching and research.This course starts with fundamental machine learning concepts and will cover advanced deep learning techniques for modeling primary computer vision and NLP tasks. The course module design helps beginners understand the underlying neural network concepts and how to apply these networks to model different important NLP and vision tasks. Simple diagrammatic illustrations help students from various backgrounds understand complex learning models. The course contents are in massive demand in AI/ML-based IT industries.INTENDED AUDIENCE: Final/Pre-final year B. Tech. (BE), M. Tech. (ME), PhD studentsINDUSTRY SUPPORT: The IT industry is looking for AI/ML professionals.
Syllabus
Week 1: Introduction to Machine Learning
Week 2:Deep Neural Network
Week 3:Deep Model for Vision
Week 4:Convolution Neural Network
Week 5:Sequential Modelling
Week 6 & 7:Generative Models
Week 8:Large Language Model
Week 9:Zero and Few Shot Learning
Week 10:DL model for Image Enhancement
Week 11:DL models for Image Classifications and Object Detection
Week 12:Multimodal Analysis and Self-Supervised Learning
- Introduction to Learning
- Machine Learning Fundamentals
- Optimizing ML Models
Week 2:Deep Neural Network
- Neural Network - Fundamentals
- Introduction to Deep Learning
Week 3:Deep Model for Vision
- Computer Vision through ML
- Deep Learning Models
Week 4:Convolution Neural Network
- CNN Architectures
- Optimizing CNN
- CNN with Residual Connections
Week 5:Sequential Modelling
- Recurrent Neural Network
- Neural Machine Translation
Week 6 & 7:Generative Models
- Generative Modelling
- Auto-regressive models
- Variational Auto-Encoder
- Generative Adversarial Network
- Diffusion Models
Week 8:Large Language Model
- Transformers
- Language Modelling
- Generative Pre-trained Transformer
Week 9:Zero and Few Shot Learning
- Zero-Shot Learning
- Few Shot Learning
Week 10:DL model for Image Enhancement
- Image Enhancement
- Deep Learning Models for Image Enhancing
Week 11:DL models for Image Classifications and Object Detection
- Image Classification, Object Detection
- DL Models for Image Classification, Object Detection.
- Medical Image Analysis and Synthetic image generation
Week 12:Multimodal Analysis and Self-Supervised Learning
- Deep models for multi-modal image and text modeling
- Semi-supervised learning, contrastive learning
- Self-supervised vision, and language modeling
Taught by
Prof. Arijit Sur