We present experimental results on supervised learning of dynam(cid:173) ical features in an analog VLSI neural network chip. The recur(cid:173) rent network, containing six continuous-time analog neurons and 42 free parameters (connection strengths and thresholds), is trained to generate time-varying outputs approximating given periodic signals presented to the network. The chip implements a stochastic pertur(cid:173) bative algorithm, which observes the error gradient along random directions in the parameter space for error-descent learning. In ad(cid:173) dition to the integrated learning functions and the generation of pseudo-random perturbations, the chip provides for teacher forc(cid:173) ing and long-term storage of the volatile parameters. The network learns a 1 kHz circular trajectory in 100 sec. The chip occupies 2mm x 2mm in a 2JLm CMOS process, and dissipates 1.2 m W.