Deep autoencoder networks have successfully been applied in unsupervised dimension reduction. The autoencoder has a "bottleneck" middle layer of only a few hidden units, ...
To cope with the increasing difference between processor and main memory speeds, modern computer systems use deep memory hierarchies. In the presence of such hierarchies, the perf...
Margaret Martonosi, Anoop Gupta, Thomas E. Anderso...
We present a novel sequential clustering algorithm which is motivated by the Information Bottleneck (IB) method. In contrast to the agglomerative IB algorithm, the new sequential ...
Asymptotic approximations are constructed for the performance measures of product form queueing networks consisting of single server, fixed rate nodes with large populations. The...
: We present a new, dynamic algorithm for test sequence compaction and test cycle reduction for combinationaland sequential circuits. Several dynamic algorithms for compaction in c...