The rod photocurrent contains two noise components that may limit the detectability of flash intensity increments. The limits imposed by the low- and high-frequency noise components were assessed by computing the performance of an optimal detector of increments in flash intensity. The limits imposed by these noise components depend on the interval of observation of the photocurrent signal. When the entire photocurrent signal, lasting 3 or more seconds, is observed, the low-frequency component of the photocurrent noise (attributed to the quantal noise of the incoming light, as well as random isomerizations of enzymes within the phototransduction cascade) is the most significant limitation on detectability. When only the first 380 ms or less is observed, the high-frequency component of the noise (due to the thermal isomerizations of the cGMP-gated channel) presents a significant limit on the detectability of flashes.

Chopper cells in the anteroventral cochlear nucleus of the cat maintain a robust rate-place representation of vowel spectra over a broad range of stimulus levels. This representation resembles that of low threshold, high spontaneous rate primary auditory nerve fibers at low stimulus levels, and that of high threshold, low spontaneous rate auditory-nerve fibers at high stimulus levels. This has led to the hypothesis that chopper cells in the anteroventral cochlear nucleus selectively process inputs from different spontaneous rate populations of primary auditory-nerve fibers at different stimulus levels. We present a computational model, making use of shunting inhibition, for how this level dependent processing may be performed within the chopper cell dendritic tree. We show that this model (1) implements level-dependent selective processing, (2) reproduces detailed features of real chopper cell post-stimulus-time histograms, and (3) reproduces nonmonotonic rate versus level functions in response to single tones measured.