Artificial Intelligence and Machine Learning for Open-world Novelty, Volume 134 in the Advances in Computers series presents innovations in computer hardware, software, theory, design and applications, with this updated volume including new chapters on AI and Machine Learning for Real-world problems, Graph Neural Network for learning complex problems, Adaptive Software platform architecture for Aerial Vehicle Safety Levels in real-world applications, OODA Loop for Learning Open-world Novelty Problems, Privacy-Aware Crowd Counting Methods for Real-World Environment, AI and Machine Learning for 3D Computer Vision Applications in Open-world, and PIM Hardware accelerators for real-world problems. Other sections cover Irregular Situations in Real-World Intelligent Systems, Offline Reinforcement Learning Methods for Real-world Problems, Addressing Uncertainty Challenges for Autonomous Driving in Real-World Environments, and more.
Please Note: This is an On Demand product, delivery may take up to 11 working days after payment has been received.
Table of Contents
PrefaceGanesh Chandra Deka
1. AI and Machine Learning for Real-world problems
Hamed Nozari, Agnieszka Szmelter-Jarosz and Javid Ghahremani
2. Graph Neural Network for learning complex problems
Chethana C
3. Adaptive Software platform architecture for Aerial Vehicle Safety Levels in real-world applications
Rakesh Shrestha, Rojeena Bajracharya and Shiho Kim
4. OODA Loop for Learning Open-world Novelty Problems
Pamul Yadav and Shiho Kim
5. Privacy-Aware Crowd Counting Methods for Real-World Environment
Sang Ho Lee, Kyuho Jeong and Shiho Kim
6. AI and Machine Learning for 3D Computer Vision Applications in Open-world
Kwanghoon Sohn
7. PIM Hardware accelerators for real-world problems
Dohyun Kim, Junghwan Choi and Shiho Kim
8. Irregular Situations in Real-World Intelligent Systems
Ashutosh Mishra and Shiho Kim
9. Offline Reinforcement Learning Methods for Real-world Problems
Taewoo Kim, Shiho Kim and Ho Suk
10. Addressing Uncertainty Challenges for Autonomous Driving in Real-World Environments
Ho Suk, Taewoo Kim, Yerin Lee and Shiho Kim
