- Neuroscience has played a key role in the history of artificial intelligence (AI), and has been an inspiration for building human-like AI, i.e. to design AI systems that emulate human intelligence. Furthermore, transferring design and processing principles from biology to computer science promises novel solutions for contemporary challenges in the field of machine learning. This research direction is called neuroscience-inspired artificial intelligence.
In addition, neuroscience provides a vast number of methods to decipher the representational and computational principles of biological neural networks, which can in turn be used to understand artificial neural networks and help to solve the so called black box problem. This endeavour is called neuroscience 2.0 or machine behaviour.
Finally, the idea of combining artificial intelligence, in particular deep learning, and computational modelling with neuroscience and cognitive science has recently gained popularity, leading to a new research paradigm for which the term cognitive computational neuroscience has been coined. There is increasing evidence that, even though artificial neural networks lack biological plausibility, they are nevertheless well suited for modelling brain function.
The seminar will cover the most important works which provide the cornerstone knowledge to understand cutting edge research at the intersection of AI and neuroscience.
Students will be able to
• independently identify challenges in translating technical solutions from the bench to the bedside, and assess how close to clinical feasibility a technical solution is
Students will have acquired competences to
• perform an unstructured literature review on an assigned subject
• independently research the assigned subject
• present and introduce the subject to their peers
• give a scientific presentation in English according to international conference standards
• summarize their findings in a written report that adheres to good scientific practice
- Empfohlene Literatur
- Barak, O. (2017). Recurrent neural networks as versatile tools of neuroscience research. Current opinion in neurobiology, 46, 1-6.
Barrett, D. G., Morcos, A. S., & Macke, J. H. (2019). Analyzing biological and artificial neural networks: challenges with opportunities for synergy?. Current opinion in neurobiology, 55, 55-64.
Cichy, R. M., Khosla, A., Pantazis, D., Torralba, A., & Oliva, A. (2016). Comparison of deep neural networks to spatio-temporal cortical dynamics of human visual object recognition reveals hierarchical correspondence. Scientific reports, 6(1), 1-13.
Cichy, R. M., & Kaiser, D. (2019). Deep neural networks as scientific models. Trends in cognitive sciences, 23(4), 305-317.
Dasgupta, S., Stevens, C. F., & Navlakha, S. (2017). A neural algorithm for a fundamental computing problem. Science, 358(6364), 793-796.
Hassabis, D., Kumaran, D., Summerfield, C., & Botvinick, M. (2017). Neuroscience-inspired artificial intelligence. Neuron, 95(2), 245-258.
Kriegeskorte, N., & Douglas, P. K. (2018). Cognitive computational neuroscience. Nature neuroscience, 21(9), 1148-1160.
Marblestone, A. H., Wayne, G., & Kording, K. P. (2016). Toward an integration of deep learning and neuroscience. Frontiers in computational neuroscience, 10, 94.
Nasr, K., Viswanathan, P., & Nieder, A. (2019). Number detectors spontaneously emerge in a deep neural network designed for visual object recognition. Science advances, 5(5), eaav7903.
Rahwan, I., Cebrian, M., Obradovich, N., Bongard, J., Bonnefon, J. F., Breazeal, C., ... & Wellman, M. (2019). Machine behaviour. Nature, 568(7753), 477-486.
Yamins, D. L., & DiCarlo, J. J. (2016). Using goal-driven deep learning models to understand sensory cortex. Nature neuroscience, 19(3), 356-365.
Jonas, E., & Kording, K. P. (2017). Could a neuroscientist understand a microprocessor?. PLoS computational biology, 13(1), e1005268.