A biologically-faithful neural substrate that learns new objects from a single exposure, knows what it doesn't know, directs its own gaze toward what surprises it, and consolidates memories during sleep. Not a neural network with biological names — a functional reproduction of the circuits that produce intelligence.
Built from first principles over multiple years. The system implements local Hebbian/BCM plasticity (no backpropagation), thalamic relay with predictive coding, hippocampal complementary learning systems, active sensing through a superior colliculus, and basal ganglia action selection by disinhibition. It runs as a living organism with a metabolic clock, developmental engine, and continual plasticity — it is not a simulation.
Learns a new object from a single exposure through hippocampal episodic binding. Multi-view understanding built through active saccade exploration.
When uncertain, reports what it doesn't know rather than hallucinating. An epistemic gate measures familiarity and confidence before committing to an answer.
Directs its own gaze via a superior colliculus with inhibition-of-return. Fixates on the most surprising part of a scene, avoids re-examining what it already knows.
Memories captured during the day consolidate during sleep through complementary learning systems replay. Episodes integrate into long-term knowledge without catastrophic forgetting.
Binds objects to locations through hippocampal place-cell analogs. Answers "where did I see that?" from episodic memory, not a lookup table.
Every fixation has a reason — novelty, unfamiliarity, goal relevance. The system explains why it looked where it looked, in mechanistic terms.
Every mechanism below is published neuroscience. The contribution is not the theory — it is making these circuits work together as a single living system.