AI CLUB · EXACT V25B MODEL · EPOCH 4
Watch a small neural network steer Snake
0 food
0 steps
0.0% walls
attract mode
LIVE INPUT
Four convolution maps
Topology inputs
Immediate danger
Current heading
Food direction
BOARD EDITOR
Draw a stress test
Fixed walls are a measured failure mode; random density is limited to 5% because denser boards tend to make this model loop.
Draw on the board, or start the empty board.
LIVE NETWORK
Hidden layers → action choice
Neuron fill shows activation. Blue/orange connections show positive/negative contributions; dashed lines are negative. These are numeric computations—not probabilities or human-like thoughts. The final decision layer combines a shared signal with three action-specific signals. The selected v26 model is constant; it was trained on sparse fixed-wall boards, not every visitor-designed environment.
TESTED ATTRACT BOARD
Empty reference · seed 99,200,057
Click anywhere to design a board
GAME COMPLETE
Final frame
HeadBodyFoodWall (moves when on a track)Track