An all-transistor circuit learns from examples in context
A simulated all-transistor learning system performs a simple in-context learning task, pointing toward hardware that can adapt from examples instead of relying only on conventional offline training. The researchers restore bidirectional signal flow in a physical circuit, then build attention from the exponential current behavior of sub-threshold MOSFETs. Training succeeds with cross-entropy loss and approximate reverse gradients, not mean squared error.