(Re)Using Qualitative Data?

The Binormalized Data-Reusing LMS Algorithm

A new algorithm, the binormalized data-reusing least mean squares (LMS) algorithm is presented. The new algorithm has been found to converge faster than other LMS-like algorithms, such as the Normalized LMS algorithm and several data-reusing LMS algorithms, when the input signal is highly correlated. The computational complexity of this new algorithm is only slightly higher than a recently prop...

Data-Reusing Recurrent Neural Adaptive Filters

A class of data-reusing learning algorithms for real-time recurrent neural networks (RNNs) is analyzed. The analysis is undertaken for a general sigmoid nonlinear activation function of a neuron for the real time recurrent learning training algorithm. Error bounds and convergence conditions for such data-reusing algorithms are provided for both contractive and expansive activation functions. Th...

Reusing Motion Data to Animate Visual Speech

In this paper we describe a technique for animating visual speech by concatenating small fragments of speech movements. The technique is analogous to the most effective audio synthesis techniques which form utterances by blending small fragments of speech waveforms. Motion and audio data is initially captured to cover the target synthesis domain; this data is subsequently phonetically labelled ...

Convergence analysis of the binormalized data-reusing LMS algorithm

3235 but with m = l = 12, only 8% of the number of flops were required for STAN 1 and about 7% for EIV-PAST. From Fig. 1, we conclude that all considered algorithms offer similar tracking accuracy. Example 2: As previously stated, one of the main advantages with STAN, compared with, for example EIV-PAST, is that estimates of the signal singular values are available. In Fig. 2, the estimated sig...

Reusing Information by Learning Models from Extreme Data Sets