Abstract Distinguishing between complex nonlinear neural time-series patterns is a challenging problem in neuroscience. Accurately classifying different patterns could be useful for a wide variety of applications, e.g. detecting seizures in epilepsy and optimizing control spaces for brain-machine interfaces. It remains challenging to correctly distinguish nonlinear time-series patterns because of the high intrinsic dimensionality of such data, making accurate inference of state changes (for intervention or control) difficult. On the one hand, simple distance metrics, which can be computed quickly, often do not yield accurate classifications; on the other hand, ensembles or deep supervised approaches offer high accuracy but are training data intensive. We introduce a reservoir-based tool, state tracker (TRAKR), which provides the high accuracy of ensembles or deep supervised methods while preserving the benefits of simple distance metrics in being applicable to single examples of training data (one-shot classification). We show that TRAKR instantaneously detects deviations in dynamics as they occur through time, and can distinguish between up to 40 patterns from different chaotic data recurrent neural networks (RNNs) with above-chance accuracy. We apply TRAKR to a benchmark time-series dataset – permuted sequential MNIST – and show that it achieves high accuracy, performing on par with deep supervised networks and outperforming other distance-metric based approaches. We also apply TRAKR to electrocorticography (ECoG) data from the macaque orbitofrontal cortex (OFC) and, similarly, find that TRAKR performs on par with deep supervised networks, and more accurately than commonly used approaches such as Dynamic Time Warping (DTW). Altogether, TRAKR allows for high accuracy classification of time-series patterns from a range of different biological and non-biological datasets based on single training examples. These results demonstrate that TRAKR could be a viable alternative in the analysis of time-series data, offering the potential to generate new insights into the information encoded in neural circuits from single-trial data.