YAP203

School of Engineering \ Artificial Intelligence Engineering

3

6

Compulsory

Turkish

-

Artificial Intelligence Engineering Undergraduate Program

Evolution of the nervous system and the origins of intelligence; neurons and neural circuits; neural coding; information processing across multiple time scales; stochastic resonance; structural and functional brain connectivity; learning and synaptic plasticity, reinforcement mechanisms and neuromodulation; predictive coding; intelligence under uncertainty; dynamical systems approaches to brain function; embodied intelligence; collective and swarm intelligence, complex adaptive systems; comparison of biological and artificial intelligence.

Textbooks:
- Augustine, G. J., Groh, J. M., Huettel, S. A., LaMantia, A.-S., White, L. E., & Purves, D. (Eds.) (2023). Neuroscience (7. baskı). Oxford University Press.
- Rosenbaum, R. (2024). Modeling neural circuits made simple with Python. MIT Press.
- Hwu, T. J., & Krichmar, J. L. (2022). Neurorobotics: Connecting the brain, body, and environment. MIT Press.

Supplementary Resources:
- Aboitiz, F. (2024). A history of bodies, brains, and minds: The evolution of life and consciousness. MIT Press.
- Gordon, D. M. (2023). The ecology of collective behavior. Princeton University Press.
- Griffiths, T. L., Chater, N., & Tenenbaum, J. B. (2024). Bayesian models of cognition: Reverse engineering the mind. MIT Press.
Sporns, O. (2010/2016). Networks of the brain. MIT Press.

The aim of the course is to introduce the biological foundations of intelligence and the mechanisms of information processing in the nervous system; to examine fundamental processes such as learning, decision making, and adaptation in the context of biological intelligence; to explore brain function from network and dynamical systems perspectives; and to establish links between artificial intelligence systems and these mechanisms and approaches. The course also aims to provide students with an interdisciplinary perspective on intelligence by discussing the similarities, differences, and limitations of biological and artificial intelligence.

1. Explain the evolution of the nervous system and the emergence of intelligence in the context of energy, connectivity, and computational constraints.
2. Explain neural information-processing mechanisms at a conceptual level and compare them with artificial systems.
3. Discuss biological and artificial intelligence systems from network-based and dynamical systems perspectives.
4. Explain learning and adaptation processes in the brain and compare these processes with learning approaches used in artificial intelligence systems.
5. Explain inference and decision-making processes under uncertainty and discuss how these processes can be modeled in artificial intelligence systems.
6. Explain intelligence at the systems level in the context of organism–environment interactions and multi-agent interactions.
7. Explain the fundamental properties of complex adaptive systems and interpret how these properties emerge.
8. Compare biological and artificial intelligence systems in terms of representation, learning, generalization, and flexibility.

Week 1: Evolution of the nervous system and the origins of intelligence: Intelligence as an adaptation under biological constraints
Week 2: The brain’s hardware: Neurons, synaptic transmission, circuits, network motifs, and 20-watt biological computation
Week 3: Neural coding and the role of noise: Rate coding, temporal coding, population coding, and stochastic resonance
Week 4: Architecture of brain networks: Structural and functional connectivity
Week 5: Mechanisms of learning: Plasticity, reinforcement dynamics, and neuromodulation
Week 6: Information processing across multiple timescales: Action potentials, oscillations, and memory processes
Week 7: Predictive coding, hierarchical information processing, and Bayesian inference
Week 8: Inference and decision making under uncertainty: Control mechanisms in biological and artificial systems
Week 9: The brain as a dynamical system: Attractor dynamics, stability, and multistability
Week 10: Embodied intelligence: The perception–action loop and brain–body–environment systems
Week 11: Collective intelligence and complex adaptive systems: From simple rules to complex behavior
Week 12: Biological and artificial intelligence: Similarities, differences, and limitations