Abstract : When several data sources are sending asynchronously without any multiplexing conventions, the stream of data from each source will be interleaved in an unpredictable sequence. In such a sequence, it would be highly desirable to deinterleave the data streams before attempting further processing. After the application of certain signal processing techniques on the incoming interleaved data stream, one obtains a feature space in which different data sources typically form distinct clusters. It is therefore essential to have a reliable clustering technique to determine: (1) the correct number of sources, and (2) the correct membership for each datum. The Hopfield-Kamgar neural net clustering technique appears to be the clustering technique of choice for this task. We explain the main aspects of our technique and briefly discuss alternative neural nets and conventional methods for clustering, in particular as applied to data deinterleaving.