Neural networks that grow themselves from noise

Kari Jaaskelainen

12 Nov 2025 — 1 min read

Nature builds brains from a single cell. This study shows how an artificial network can do something similar - growing itself from "noise".

Inspired by the early visual system (retina to LGN), the authors propose a simple developmental algorithm that starts with one "cell" and self-organizes a functional, layered network. The key ingredients: spontaneous, wave-like activity in the first layer (random-looking but structured) and a local learning rule in the second layer that captures that pattern. Together, they wire up a convolutional pooling layer - no hand-designed architecture required.

Why it matters: the method adapts to many input geometries, tolerates malfunctioning units, and can grow different pool sizes and shapes. It’s a primitive but concrete step toward AI systems that develop rather than being painstakingly engineered.

Paper: http://arxiv.org/abs/1906.01039v1

Authors: Guruprasad Raghavan, Matt Thomson

Paper: http://arxiv.org/abs/1906.01039v1

Register: https://www.AiFeta.com

AI NeuralNetworks DeepLearning SelfOrganization BioInspired Neuroscience MachineLearning Research

Automating GDPR Compliance: A Roadmap for Companies and Law Firms

GDPR compliance is more than checkboxes. A new roadmap from the Privatech project shows how automation and machine learning can help companies and law firms assess—and even generate—privacy compliance. * Shift the focus to data processors’ real workflows: drafting policies, mapping data uses, documenting decisions. * Break compliance into machine-ready

FPGAs for Faster, Leaner Deep Learning: A Review of CNN Accelerators

Deep learning drives image search, robots, and medical scans. Most systems lean on CPUs and GPUs. This review asks: what if we run convolutional neural networks (CNNs) on FPGAs—reconfigurable chips you can tailor to the model? * Why FPGAs: custom dataflows, low latency, and strong energy efficiency—great for cameras,

Dynamic-K: Recommendations That Know When to Stop

Most apps show a fixed number of “top” items—say 10 movies or 20 products—assuming there are always enough good options. But that’s not always true: sometimes there are few relevant items, or some users are extra picky. The result? Filler recommendations. Dynamic-K flips the script. Instead of

Teaching chatbots to stop contradicting themselves (DECODE)

Teaching chatbots to stop contradicting themselves Ever had a bot say one thing, then the opposite a few turns later? This study introduces DECODE—a new task and dataset for spotting contradictions in everyday conversations, drawn from both human-human and human-bot chats. * New data beats existing natural language inference (NLI)

Read more

Automating GDPR Compliance: A Roadmap for Companies and Law Firms

FPGAs for Faster, Leaner Deep Learning: A Review of CNN Accelerators

Dynamic-K: Recommendations That Know When to Stop

Teaching chatbots to stop contradicting themselves (DECODE)