as the level of inputs correlation changes, but also the values of total power consumption. For example, for duke2, the total power estimated under weakly correlated inputs was 3611.67 uW, while this value for strongly correlated inputs was 820.87 uW (there is a factor of 4 between the two). The same behavior has been observed for other circuits.To conclude, input pattern dependencies (in parti...

This paper illustrated an application of Locally Weighted Projection Regression to a complex robot learning task. The O(n) update complexity of LWPR, together with its statistically sound dimensionality reduction and learning rules allowed a reliable and successful real-time implementation of the algorithm on an actual anthropomorphic robot. From the viewpoint of learning control, these results...

This study demonstrates the ecacy of neural implementations of multistage and tree-search quantization. For xed branching ratio we have seen that the tree-search quantizer consistently outperforms the multi-stage structure, though at considerable resource cost. For networks with equal neural resource, the multistage architecture returns signicantly lower mse than the at and tree-search architec...

A case-control comparison of immunologic and psychological parameters in the multiple chemical sensitivity syndrome. This letter is prompted by Rall's editorial on media and science in the January issue of EHP (102:10). Rall implies that bad reporting is being conducted concerning dioxin, CFCs, and asbestos. Rall concludes by assuming that he is correct in assigning a high level of risk to each...

We presented in some detail our natural language information retrieval system consisting of an advanced NLP module and a `pure' statistical core engine. While many problems remain to be resolved, including the question of adequacy of term-based representation of document content, we attempted to demonstrate that the architecture described here is nonetheless viable. In particular , we demonstra...

Finally, some preliminary results from simulations are reported. The experiments employed the Markov channel models as configured in 4.1 and the evaluation module of 3.2 with α = 15%, applied to a transmissions of the well-known Foreman sequence in QCIF format at 9.6 kb/s. The video codec was the H.263 TMN [3], i.e., without error correction and concealment techniques. Fig. 7 shows the above in...