- Assuring quality, accuracy, model resilience, and more characteristics in cases of AI business solution development, and guaranteeing performance, and outcomes. Interaction AI Use Cases.
- Level -Basic - Choice - Specialisation
- Prerequisites - Introduction to Interaction AI or any introduction course
- Assessments - Micro Assessment weekly, Full Assessment last week.
Week 1 - Perfecting Human Interaction Recognition
Learning OutcomeStudents will perfect recognition of human interactions, gestures, and expressions, enabling seamless engagement in AI-driven interactions.
1.1 Stack of Gesture and Expression Recognition Algorithms with Constraints Evaluation.
1.2 Medical and Assistive Interaction Use Case.
1.3 Multi-User and Group Interaction Use Cases.
Practical Component
Practical demonstrations on various interaction detection models, evaluating their strengths and limitations. Students will create models and assess their real-world applications.
Week 2 - Multi-Modal Speech and Text Fusion
Learning OutcomePerfecting AIs ability to integrate speech, text, and context for better interaction.
2.1 Combining real-time speech recognition with text-based input processing.
2.2 Context Awareness through Sentiment and Intonation Analysis.
2.3 Handling multi-lingual interactions and response generation.
Practical Component
Students will experiment with and refine speech-text interaction models, integrating contextual AI to improve response accuracy and relevance.
Week 3 -Integrating Vision and Spatial Awareness
Learning OutcomeCapturing depth, spatial awareness, and 3D environments for better AI-driven interactions.
3.1 Using multi-camera depth-based approaches for object and user recognition.
3.2 Understanding 3D coordinates of interactions for virtual and augmented experiences.
3.3 Question answering for various spatial scenarios based on visual input.
Practical Component
Demonstrations of AI-enabled spatial awareness, followed by hands-on exercises in realtime 3D object interaction and environmental understanding.
Week 4 - Real-Time Interaction AI for Dynamic Environments
Learning OutcomeUnderstanding and optimizing AI interaction in live, unpredictable settings such as public spaces, vehicles, or customer service applications
4.1 AI-driven recognition and response in crowded, dynamic environments.
4.2 Handling interruptions, multiple users, and varied contexts in real-time.
4.3 Optimizing response speed while maintaining contextual accuracy.
Practical Component
Hands-on implementation of AI-powered real-time interaction systems, testing their effectiveness across various unpredictable scenarios.
Week 5- Integrating Multiple Models for Intelligent Interaction
Learning OutcomeStudents will learn to integrate multiple AI models (vision, speech, text, and spatial) to create cohesive, responsive, and intelligent systems.
5.1 Transfer Learning for fine-tuning models for unique user interactions.
5.2 Problem decomposition and serial model approaches for complex interactions.
5.3 Multi-modal AI fusion for complete real-time responsiveness.
Practical Component
Students will integrate multiple AI capabilities to create seamless, end-to-end interaction solutions for specialized use cases.
Week 6 -Project and Assessment
Learning OutcomeStudents will work on a custom project of choice, selected by the group, to be completed within a week. The project will be peer-reviewed, with a final presentation of outcomes.
6.1 Data Selection, Preparation, Algorithm Selection, and Initial Training Day.
6.2 Self-Assessment, Peer Assessment, and Review of Outcomes.
6.3 Final Presentations and Scoring of Achieved Outcomes.
Practical Component
Students will present their AI-driven interaction projects, demonstrating their effectiveness in real-world scenarios and receiving feedback from peers and prospective recruiters.