VVZ API is not affiliated with ETH Zurich. Data might be outdated or incorrect. Please view the official ETHZ Vorlesungsverzeichnis for binding information.

227-0421-00L 4 Credits MSC , WBZ , NDS D-HEST , D-MAVT , D-MATH , D-PHYS , D-ITET , D-INFK
You're viewing possible stale or outdated data. Please check the latest semester for more up-to-date information.

Learning in Deep Artificial and Biological Neuronal Networks

Lecturers & Examiners: Prof. Dr. Benjamin Grewe
VVZ CR n/a

Last Updated: 2026-02-05 16:15:35

Abstract

Deep-Learning (DL) a brain-inspired weak for of AI allows training of large artificial neuronal networks (ANNs) that, like humans, can learn real-world tasks such as recognizing objects in images. However, DL is far from being understood and investigating learning in biological networks might serve again as a compelling inspiration to think differently about state-of-the-art ANN training methods.

Objective

The main goal of this lecture is to provide a comprehensive overview into the learning principles neuronal networks as well as to introduce a diverse skill set (e.g. simulating a spiking neuronal network) that is required to understand learning in large, hierarchical neuronal networks. To achieve this the lectures and exercises will merge ideas, concepts and methods from machine learning and neuroscience. These will include training basic ANNs, simulating spiking neuronal networks as well as being able to read and understand the main ideas presented in today’s neuroscience papers. After this course students will be able to: - read and understand the main ideas and methods that are presented in today’s neuroscience papers - explain the basic ideas and concepts of plasticity in the mammalian brain - implement alternative ANN learning algorithms to ‘error backpropagation’ in order to train deep neuronal networks. - use a diverse set of ANN regularization methods to improve learning - simulate spiking neuronal networks that learn simple (e.g. digit classification) tasks in a supervised manner.

Content

Deep-learning a brain-inspired weak form of AI allows training of large artificial neuronal networks (ANNs) that, like humans, can learn real-world tasks such as recognizing objects in images. The origins of deep hierarchical learning can be traced back to early neuroscience research by Hubel and Wiesel in the 1960s, who first described the neuronal processing of visual inputs in the mammalian neocortex. Similar to their neocortical counterparts ANNs seem to learn by interpreting and structuring the data provided by the external world. However, while on specific tasks such as playing (video) games deep ANNs outperform humans (Minh et al, 2015, Silver et al., 2018), ANNs are still not performing on par when it comes to recognizing actions in movie data and their ability to act as generalizable problem solvers is still far behind of what the human brain seems to achieve effortlessly. Moreover, biological neuronal networks can learn far more effectively with fewer training examples, they achieve a much higher performance in recognizing complex patterns in time series data (e.g. recognizing actions in movies), they dynamically adapt to new tasks without losing performance and they achieve unmatched performance to detect and integrate out-of-domain data examples (data they have not been trained with). In other words, many of the big challenges and unknowns that have emerged in the field of deep learning over the last years are already mastered exceptionally well by biological neuronal networks in our brain. On the other hand, many facets of typical ANN design and training algorithms seem biologically implausible, such as the non-local weight updates, discrete processing of time, and scalar communication between neurons. Recent evidence suggests that learning in biological systems is the result of the complex interplay of diverse error feedback signaling processes acting at multiple scales, ranging from single synapses to entire networks.

Resources

Lecture Notes

The lecture slides will be provided as a PDF after each lecture.

General Information

Language
English
Levels
MSC , WBZ , NDS
Frequency
Yearly recurring

Examination

Type
session examination
Mode
written 120 minutes
Aids
None
The lectures are complemented with project work that will span across 14 lectures and comprise of 7 projects that have to be handed in on a bi-weekly basis. At the end, the learning objectives will be evaluated through a written session exam which will determine the course grade. Similar to the course, the session exam will consist of 50% biology and 50% machine learning questions. To be admitted to the session exam at least 5 out of 7 projects need to be handed in and evaluated as passed. It is not necessary to re-take the project work for a re-sit of the exam.

Course Components

Type Title Time & Place Hours
lecture with exercise Learning in Deep Artificial and Biological Neuronal Networks
  • Wed 09:15-12:00 (ML F 34)
3 h weekly

Offered In