The paper proposes a method for task adaptation that eliminates the need for gradient computation during adaptation. Using a Neural Cellular Automaton, the authors train recurrent dynamics and memory read/write operations via backpropagation, then fix the slow model parameters. Online adaptation is achieved solely through local memory updates driven by prediction errors, enabling significant performance gains on new classification tasks with a single support set pass.
By Krsto Prorokovi\'c
Neural Cellular Automata (NCAs) are shown to learn general, scale‑invariant topological primitives in their hidden channels, which can be transferred from a teacher to a student model for few‑shot learning. The study introduces a transfer‑learning mechanism that injects pretrained hidden states into a student, improving early optimization and outperforming recurrent and feed‑forward baselines on MNIST benchmarks with only ~9,800 parameters. Mechanistic analysis reveals that hidden channels decouple feature extraction from classification, converging to mutually orthogonal states that absorb morphological complexity.
By Etienne Guichard, Stefano Nichele
arXiv:2608. 14019v1 Announce Type: cross Abstract: Emergent Models (EMs) are a machine learning paradigm based on simple yet open-ended substrates, such as cellular automata, in which modeling is treated not as the learning of a closed-form input-output map but as the emergence, within simple dynamical systems, of computational behaviors that solve external tasks.
By Giacomo Bocchese, Nicola Giacobbo, Etienne Guichard, James Wiles, Akshaj Devireddy
arXiv:2511. 10119v4 Announce Type: replace Abstract: We propose a new perspective for approaching artificial general intelligence (AGI) through an intelligence foundation model (IFM).
By Borui Cai, Yao Zhao
arXiv:2606. 23587v2 Announce Type: replace Abstract: Previous work has found a gap between the scale of neural networks that reliably learn Conway's Game of Life, and minimal networks capable of representing the classic cellular automaton with hard-coded parameter values.
By Tashin Ahmed, Q. Tyrell Davis
arXiv:2608. 04358v1 Announce Type: new Abstract: Continual learning (CL) requires models to learn tasks sequentially, yet deep neural networks often suffer from plasticity loss and poor knowledge transfer, which can impede their long-term adaptability.
By Seyed Roozbeh Razavi Rohani, Khashayar Khajavi, Wesley Chung, Mandana Samiei, Mo Chen
arXiv:2405. 02369v2 Announce Type: replace-cross Abstract: In the past decade, many successful networks are on novel architectures, which almost exclusively use the same type of neurons.
By Feng-Lei Fan, Meng Wang, Hang-Cheng Dong, Jianwei Ma, Tieyong Zeng
arXiv:2604. 27031v2 Announce Type: replace-cross Abstract: In a continual learning setting, we require a model to be plastic enough to learn a new task and stable enough to not disturb previously learned capabilities.
By Karthik Charan Raghunathan, Christian Metzner, Laura Kriener, Melika Payvand
arXiv:2608. 02606v1 Announce Type: new Abstract: Fault tolerance in classical computing has traditionally relied on static strategies like hardware redundancy and error-correcting codes.
By Marcello Barylli, Gabriel B\'ena, Alexander Mordvintsev, Eleni Nisioti, Sebastian Risi
arXiv:2606. 28380v1 Announce Type: cross Abstract: The intricate structures of biological neural networks largely emerge during development, guided by a comparatively compressed blueprint encoded in the genome.
By Mani Hamidi, Sina Khajehabdollahi, Charley M. Wu, Emmanouil Giannakakis
arXiv:2512. 12713v2 Announce Type: replace-cross Abstract: Control policies are often implemented with fixed-capacity multilayer perceptrons trained by backpropagation, which require architecture selection in advance and cannot adapt their capacity during learning.
By Yiyang Jia, Chengxu Zhou
arXiv:2606. 30669v1 Announce Type: cross Abstract: Backpropagation-trained dense neural networks are powerful function approximators, but they couple learning across many parameters and can overwrite previous associations when tasks conflict.
By Xingcheng Fu, Xianjun Chen, Zhihao Li