Despite major advances in artificial intelligence, especially in the field of neural networks, these systems still pale in comparison to even simple biological intelligence. Current machine learning systems take many trials to learn, lack common-sense, and often fail even if the environment only changes slightly. The enormous potential of autonomous machines remains unfulfilled and we still lack robots to fill our dishwashers or go on autonomous search-and-rescue missions. The grand goal of GROW-AI is to create machines with a more general intelligence, allowing rapid adaption in unknown situations. In stark contrast to current neural networks, whose architectures are designed by human experts and whose large number of parameters are optimized directly, evolution does not operate directly on the parameters of biological nervous systems. Instead these nervous systems display developmental growth self-organized through a much smaller genetic program that produces rich behavioral capabilities right from birth and the ability to rapidly learn. Neuroscience suggests this “genomic bottleneck” is an important regularizing constraint, allowing animals to generalize to new situations. However, currently there does not exist a solution to creating a similar system artificially. We address this challenge with two ambitious ideas. First, we will learn genomic bottleneck algorithms instead of manually designing them, exploiting recent advances in memory-augmented deep neural networks that can learn complex algorithms. In addition, we will co-optimize task generators that provide the agents with the most effective learning environments. Exploiting ideas from artificial life, self-organization, neurobiology, and machine learning, we will investigate if algorithmic growth is needed to understand and create intelligence. If successful, this project will greatly improve the autonomy of machines and significantly increase the range of real-world tasks they can solve.


Sebastian Risi – principal investigator
Eleni Nisioti – postdoc
Erwan Plantec – PhD student
Joachim W. Pedersen – postdoc
Milton L. Montero – postdoc

Elias Najarro – affiliated PhD
Shyam Sudhakaran – affiliated researcher

Seeking new PhD for 2024 or early 2025 – contact me

Advisory board

Kevin Mitchell – neurogenetics
Robin Hiesinger – neurogenetics
Tony Zador – neuroscience

Selected Recent GROW-AI Papers

Evolving Self-Assembling Neural Networks: From Spontaneous Activity to Experience-Dependent Learning
Erwan Plantec, Joachim W. Pedersen, Milton L. Montero, Eleni Nisioti, and Sebastian Risi
Proceedings of the 2024 Conference on Artificial Life (ALIFE 2024)

Growing Artificial Neural Networks for Control: the Role of Neuronal Diversity
Eleni Nisioti, Erwan Plantec, Milton Montero, Joachim Winther Pedersen, Sebastian Risi
In Proceedings of the Companion Conference on Genetic and Evolutionary Computation, 2024.

Meta-Learning an Evolvable Developmental Encoding
Milton L. Montero, Erwan Plantec, Eleni Nisioti, Joachim W. Pedersen, and Sebastian Risi
Proceedings of the 2024 Conference on Artificial Life (ALIFE 2024)

Structurally Flexible Neural Networks: Evolving the Building Blocks for General Agents
Joachim Winther Pedersen, Erwan Plantec, Eleni Nisioti, Milton Montero, Sebastian Risi
In Proceedings of Conference on Genetic and Evolutionary Computation (GECCO), 2024.

Towards Self-Assembling Artificial Neural Networks through Neural Developmental Programs
Elias Najarro, Shyam Sudhakaran, and Sebastian Risi
The 2023 Conference on Artificial Life

Earlier Foundational Papers

HyperNCA: Growing Developmental Networks with Neural Cellular Automata
Elias Najarro, Shyam Sudhakaran, Claire Glanois, Sebastian Risi
From Cells to Societies: Collective Learning across Scales 2022 ICLR Workshop

Evolving and Merging Hebbian Learning Rules: Increasing Generalization by Decreasing the Number of Rules
Joachim Winther Pedersen and Sebastian Risi
Proceedings of the Conference on Genetic and Evolutionary Computation (GECCO 2021). New York, NY: ACM.

Meta-Learning through Hebbian Plasticity in Random Networks
Elias Najarro and Sebastian Risi
Thirty-fourth Conference on Neural Information Processing Systems (NeurIPS 2020)