Track 1: Deep Learning Fundamentals
- Deep Neural Networks
- Deep Neural Networks Optimization Algorithms
- Deep Feedforward Networks
- Regularization
- Deep Convolutional Neural Networks
- Deep Recurrent Neural Networks
- Sequence Modelling
- Loss functions, and training methodologies.
- Theoretical foundations and mathematical concepts behind Deep Learning
- Applications of deep learning in various engineering streams
Track 2: Visual Artificial Intelligence
- Object detection, image segmentation, and image recognition using deep learning.
- Image Generation and Style Transfer.
- Blockchain for computer vision/AI provenance
- Quantum Machine Learning In Computer Vision
- Visual feature extraction and dimensionality reduction.
- Computer vision system security using blockchain
Track 3: Natural Language Processing and Multimodal Learning
- Deep learning for text and speech processing.
- Combining visual and textual information for improved understanding.
- Multimodal fusion for applications such as image captioning and sentiment analysis.
Track 4: Deep Reinforcement Learning
- Deep Q-Networks (DQN) and policy gradient methods.
- Deep Belief Networks and Statistical Learning
- Reinforcement learning in robotics and autonomous systems.
- Applications in game playing and autonomous navigation.
Track 5: Generative Adversarial Networks (GANs)
- GAN architecture, training, and applications in image synthesis.
- Conditional GANs and their use in various domains.
- Deep Generative Models
- Ethical considerations and challenges of GAN-generated content.
Track 6: Transfer Learning and Pretrained Models
- Inference Dependencies on Multi-Layered Networks
- Tensors for Deep Learning
- Multi-Scale Deep Architecture and Learning
- Fine-tuning pre-trained models.
- Knowledge transfer and domain adaptation in deep learning.
- Practical use cases for transfer learning.
Track 7: Interpretability and Explainability
- Methods for understanding and interpreting deep learning models.
- Training schemes, GPU computation, and paradigms
- Explainable AI (XAI) techniques and their importance in real-world applications.
- Visualizing and explaining model decisions.
Track 8: Applications of Deep Learning in Healthcare
- Medical image analysis and diagnosis using deep learning.
- Predictive modeling for disease diagnosis and patient outcomes.
- Ethical and regulatory aspects of AI in healthcare.
Track 9: Deep Learning for Autonomous Systems
- Autonomous Computing
- Self-driving cars and autonomous drones.
- Smart cities and intelligent transportation systems.
- Deep learning in industrial automation and manufacturing.
- Extreme Learning Machines
- Hybrid Intelligent Systems
Track 10: Ethical and Societal Implications
- Discussion of ethical concerns in deep learning and AI.
- Bias and fairness in AI algorithms.
- Representation embedding spaces
- Societal impacts and the responsible use of AI technology.
Track 11: Industry and Business Applications
- Quantum Deep Learning
- Case studies and real-world implementations of deep learning.
- Startups and innovation in deep learning.
- Deep learning in finance, marketing, and other sectors.
Track 12: Future Trends and Research Directions
- Emerging trends in deep learning and visual AI.
- Cross-disciplinary collaborations and future research areas.
- Applications of deep learning in various engineering streams
- Challenges and opportunities in the field.
