This title appears in the Scientific Report :
2023
Please use the identifier:
http://dx.doi.org/10.34734/FZJ-2023-03569 in citations.
Gradient-Free Optimization of Artificial and Biological Networks using Learning to Learn
Gradient-Free Optimization of Artificial and Biological Networks using Learning to Learn
Understanding intelligence and how it allows humans to learn, to make decision and form memories, is a long-lasting quest in neuroscience. Our brain is formed by networks of neurons and other cells, however, it is not clear how those networks are trained to learn to solve specific tasks. In machine...
Saved in:
Personal Name(s): | Yegenoglu, Alper (Corresponding author) |
---|---|
Contributing Institute: |
Jülich Supercomputing Center; JSC |
Imprint: |
Jülich
Forschungszentrum Jülich GmbH Zentralbibliothek, Verlag
2023
|
Physical Description: |
149 |
Dissertation Note: |
Dissertation, RWTH Aachen University, 2023 |
ISBN: |
978-3-95806-719-6 |
DOI: |
10.34734/FZJ-2023-03569 |
Document Type: |
Book Dissertation / PhD Thesis |
Research Program: |
Center for Simulation and Data Science (CSD) - School for Simulation and Data Science (SSD) Helmholtz School for Data Science in Life, Earth and Energy (HDS LEE) JL SMHB - Joint Lab Supercomputing and Modeling for the Human Brain (JL SMHB-2021-2027) Human Brain Project Specific Grant Agreement 3 Domain-Specific Simulation & Data Life Cycle Labs (SDLs) and Research Groups SimLab Neuroscience Doktorand ohne besondere Förderung |
Series Title: |
Schriften des Forschungszentrums Jülich IAS Series
55 |
Link: |
OpenAccess |
Publikationsportal JuSER |
Understanding intelligence and how it allows humans to learn, to make decision and form memories, is a long-lasting quest in neuroscience. Our brain is formed by networks of neurons and other cells, however, it is not clear how those networks are trained to learn to solve specific tasks. In machine learning and artificial intelligence it is common to train and optimize neural networks with gradient descent and backpropagation. How to transfer this optimization strategy to biological, spiking networks (SNNs) is still a matter of research. Due to the binary communication scheme between neurons of an SNN via spikes, a direct application of gradient descent and backpropagation is not possible without further approximations. In my work, I present gradient-free optimization techniques that are directly applicable to artificial and biological neural networks. I utilize metaheuristics, such as genetic algorithms and the ensemble Kalman Filter, to optimize network parameters and train networks to learnto solve specific tasks. The optimization is embedded into the concept of meta-learning and learning to learn respectively. The learning to learn concept consists of a two loop optimization procedure. In the first, inner loop the algorithm or network is trained on a family of tasks, and in the second, outer loop the hyper-parameters and parameters of the network are optimized. First, I apply the EnKF on a convolution neural network, resulting in high accuracy when classifying digits. Then, I employ the same optimization procedure on a spiking reservoir network within the L2L framework. The L2L framework, an implementation of the learning to learn concept, allows me to easily deploy and execute multiple instances of the network in parallel on high performance computing systems. In order to understand how the network learning evolves, I analyze the connection weights over multiple generations and investigate a covariance matrix of the EnKF in the principle component space. The analysis not only shows the convergence behaviour of the optimization process, but also how sampling techniques influence the optimization procedure. Next, I embed the EnKF into the L2L inner loop and adapt the hyper-parameters of the optimizer using a genetic algorithm (GA). In contrast to the manual parameter setting, the GA suggests an alternative configuration. Finally, I present an ant colony simulation foraging for food while being steered by SNNs. While training the network, self-coordination and self-organization in the colony emerges. I employ various analysis methods to better understand the ants’ behaviour. With my work I leverage optimization for different scientific domains utilizing meta-learning and illustrate how gradient-free optimization can be applied on biological and artificial networks. |