Home▸Machine Learning & Neural Networks▸Neural Network Dynamics in 3D - Spiking Signal Cascades

🧠 Neural Network Dynamics in 3D - Spiking Signal Cascades

3D companion to the 2D neural network simulator: neurons sit in a 3D volume, each wired to its nearest neighbours, and a spike travels along every synapse and fires the next neuron. Orbit the network, click neurons to trigger cascades, drag them to reshape the wiring, and tune refractory period and spontaneous firing to see sparse, reverberating or runaway activity.

Machine Learning & Neural Networks3DEasy60 FPS📱 Mobile-adapted⇄ 2D version

Details

CategoryMachine Learning & Neural Networks

RenderingThree.js · WebGL

DifficultyEasy

Target FPS60

ControlsDrag to orbit, scroll to zoom, click a neuron to fire it, drag a neuron to move it; sliders for neuron count, signal speed, nearest targets, connection probability, refractory period and spontaneous firing; presets, Pause, Step, Random spike, Reset, Rewire and Auto-rotate, with live neuron, synapse, spike and firing-rate readouts and an activity graph.

neural networkneuronssynapsespikingnetwork dynamicswebgl3d-simulation

Related simulations

Decision Tree LiveCART decision tree with Gini impurity splitting; axis-aligned splits emerge level by level…

Reinforcement LearningQ-learning agent navigates an 8×8 grid maze. Heatmap shows max Q-values; white arrows show…

Self-Organising Map24×24 Kohonen SOM (576 neurons, 3D RGB input). Gaussian neighbourhood update as α and σ… ⊞ All 262 in Machine Learning & Neural Networks →

⚙ Under the hood

neural networkneuronssynapsespikingnetwork dynamicswebgl3d-simulation

3D · Three.js / WebGL renderer · 60 FPS target · runs fully client-side, no install