2 citations · 2 across the 6 of their papers we have counts for
7 papers
Architecture Generalization with MetaNCA
Meet Barot, Daniel Berenberg, Sina Khajehabdollahi
Self-organization is an emergent property of life, driven by the collective behavior of individual components acting on local information. Biological neurons, through local interac…
Distilling a Modular Reservoir Through a Genomic Bottleneck
Mani Hamidi, Sina Khajehabdollahi, Charley M. Wu +1
The intricate structures of biological neural networks largely emerge during development, guided by a comparatively compressed blueprint encoded in the genome. The connectivity tha…
Expedition & Expansion: Leveraging Semantic Representations for Goal-Directed Exploration in Continuous Cellular Automata
Sina Khajehabdollahi, Gautier Hamon, Marko Cvjetko +3
Discovering diverse visual patterns in continuous cellular automata (CA) is challenging due to the vastness and redundancy of high-dimensional behavioral spaces. Traditional explor…
Modular Growth of Hierarchical Networks: Efficient, General, and Robust Curriculum Learning
Mani Hamidi, Sina Khajehabdollahi, Emmanouil Giannakakis +3
Structural modularity is a pervasive feature of biological neural networks, which have been linked to several functional and computational advantages. Yet, the use of modular archi…
Network bottlenecks and task structure control the evolution of interpretable learning rules in a foraging agent
Emmanouil Giannakakis, Sina Khajehabdollahi, Anna Levina
Developing reliable mechanisms for continuous local learning is a central challenge faced by biological and artificial systems. Yet, how the environmental factors and structural co…
Emergent mechanisms for long timescales depend on training curriculum and affect performance in memory tasks
Sina Khajehabdollahi, Roxana Zeraati, Emmanouil Giannakakis +3
Recurrent neural networks (RNNs) in the brain and in silico excel at solving tasks with intricate temporal dependencies. Long timescales required for solving such tasks can arise f…