Neuromorphic Computing from the Computer Science Perspective - Algorithms and Applications

Overview

Syllabus

• Introduction to Neuromorphic Computing
Definition and overview
Historical context and evolution
Importance in modern computing paradigms
• Fundamentals of Spiking Neural Networks (SNNs)
Biological inspiration
Neuron models: LIF, Izhikevich, and others
Encoding and decoding information
• Algorithmic Foundations of Neuromorphic Systems
Learning algorithms: STDP, reinforcement learning
Network architectures and topologies
Implementation challenges and optimization strategies
• Neuromorphic Hardware Architectures
Overview of existing hardware: IBM TrueNorth, Intel Loihi
Custom neuromorphic chips: features and capabilities
Comparisons with traditional computing architectures
• Applications in Scientific Data Analysis
Pattern recognition and classification
Real-time data processing
Case studies: astronomy, neuroscience, and climate modeling
• Applications in Autonomous Systems
Real-time sensor processing
Decision-making in autonomous vehicles
Integration challenges in complex systems
• Future Directions and Research Frontiers
Emerging trends in neuromorphic computing
Opportunities in AI and machine learning
Open research questions and technological gaps
• Course Summary and Project
Recap of key concepts
Presentation of student projects
Future learning pathways and resources

---

Subjects

Computer Science