Home▸AI & Machine Learning▸2D Neural Network Forward Pass 2

2D Neural Network Forward Pass 2

Interactive 2D diagram of a feed-forward neural network: set the layer sizes, pick an activation function, drag the input values, and watch the weighted-sum-plus-activation math flow forward layer by layer as animated pulses and node brightness, with per-node values on hover.

AI & Machine Learning2DModerate60 FPS📱 Mobile-adapted⇄ 3D version

Details

CategoryAI & Machine Learning

RenderingCanvas 2D

DifficultyModerate

Target FPS60

ControlsDrag input-value sliders or set the layer sizes (input/hidden/output neuron counts), pick sigmoid, tanh, ReLU or linear activation, click Run forward pass to animate the computation edge by edge, toggle auto-animate for continuously drifting inputs, or randomize the weights — hover any node for its exact pre-activation and activation values.

neural networkforward passactivation functionweighted sumdeep learningartificial intelligenceperceptron

Related simulations

Gradient Descent VisualiserWatch SGD, Momentum, RMSprop and Adam navigate a 3D loss landscape in real time. Compare…

K-Means Clustering — Machine Learning VisualiserVoronoi regions and centroid trails update as K-Means++ steps through blob, half-moon or…

Convolutional Neural NetworkA filter scans an 8×8 image layer by layer — watch convolution, ReLU activation and… ⊞ All 1191 in AI & Machine Learning →

This simulator draws a fully-connected feed-forward neural network as a flat, editable diagram instead of a rotating 3D scene. Set the number of input and output neurons, choose one to three hidden layers with their own neuron counts, and pick an activation function — sigmoid, tanh, ReLU, or linear identity. Dragging an input slider re-computes the real weighted-sum-plus-bias math for every neuron and instantly updates each node's color and brightness to match its activation, while the "Run forward pass" button animates the same computation as pulses traveling along the weighted edges from the input layer to the output layer, one hop at a time. Hovering any neuron reveals its exact pre-activation sum and post-activation value, and the output panel tracks the network's final numbers live as you experiment with architecture, weights, and inputs.

⚙ Under the hood

Interactive 2D diagram of a feed-forward neural network: configure the layer sizes, choose an activation function, drag the input values, and watch the real weighted-sum-plus-activation math flow forward as animated pulses and node brightness, with exact per-node values on hover.

neural networkforward passactivation functionweighted sumdeep learningartificial intelligenceperceptron

2D · HTML5 Canvas 2D · 60 FPS target · runs fully client-side, no install