Bio Mirror / Circuit
Circuits and Plasticity
Above the single cell, function comes from how cells are wired together: excitation balanced against inhibition, recurrent loops that sustain activity, and neuromodulatory systems that reconfigure the whole assembly according to context. This is the level at which reinforcement learning was discovered twice — once in psychology and once in the midbrain.
Connectivity is the program. Learning edits the wiring, and the wiring constrains what can be learned.
Population Coding
Meaning lives in the pattern across many cells, not in any one of them.
Biology
The represented quantity is recoverable from the population as a weighted vector sum — Georgopoulos showed in the 1980s that the direction of an arm movement can be read out of motor cortex this way, …
In AI
This is the direct biological precedent for representing features as directions in activation space rather than as individual neurons. Broad tuning is polysemanticity; distributed representation over a fixed population is superposition. Neuroscience arrived at the …
In Robotics
Sensor fusion and probabilistic state estimation: no single sensor determines the state, and the estimate is a weighted combination whose reliability exceeds any individual input. A population vector readout and a Kalman filter are solving …
Basal Ganglia and the Dopamine Signal
A selection circuit trained by a reward prediction error — reinforcement learning, implemented in tissue.
Biology
The basal ganglia select among competing actions and learn which selections were worth making. Schultz's recordings showed that midbrain dopamine neurons fire not to reward itself but to reward that was better or worse than …
In AI
Temporal-difference reinforcement learning, and therefore the reward-model machinery in RLHF. The actor-critic architecture maps onto the circuit surprisingly well: the striatum as actor selecting actions, the dopamine signal as the critic's error term. The convergence …
In Robotics
Behavior arbitration in a subsumption or behavior-tree architecture: multiple candidate controllers compete, and a selection layer decides which one gets the actuators. The inhibition-by-default design is also good engineering — a robot whose actions must …
Lesions, Compensation, and the Limits of Ablation
A century of inferring function from damage — including every mistake interpretability is now positioned to repeat.
Biology
The method works, within limits that took decades to characterize. Diaschisis: damage to one region disrupts distant regions that depended on its input, so the deficit maps larger than the lesion. Compensation: surviving tissue reorganizes, …
In AI
Ablation studies in interpretability are lesion studies, and every caveat transfers intact. Backup behavior in transformers — where ablating a head causes another to take over its role — is compensation, observed on a timescale …
In Robotics
Fault injection and degraded-mode testing: disable a sensor or actuator and characterize what the system does. Good robotics practice already assumes compensation and redundancy, and measures graceful degradation rather than binary failure.