artificial neural networks

Neural networks can grow their own learning rules from simple wiring

Randomly wired neural networks can grow their own learning rules from scratch. MIT researchers showed that simple, shared plasticity rules, not a pre-designed algorithm, let these networks assemble learning motifs and match backpropagation's performance on image classification. That's a different approach: specify local rules, let the machinery organize itself. The authors aren't claiming the brain works this way, but the biological plausibility is compelling. It invites us to explore how learning emerges from wiring, not just code.