James Ting-Ho Lo

Learn More
  • Book Reviews, Spective—i W Sandberg, +12 authors J D Powell
  • IEEE Transactions on Neural Networks
  • 2004
This book provides an in-depth, comprehensive treatment of artificial learning and adaptive systems of the feedforward neural network type. Chapter topics include an overview and brief history of feedback control, dynamic models, dynamic response, properties of feedback, nonlinear neural networks, and speech recognition. It is a basic reference concerning(More)
As opposed to the analytic approach used in the modern theory of optimal filtering, a synthetic approach is presented. The signalhensor data, which are generated by either computer simulation or actual experiments, are synthesized into a filter by training a recurrent multilayer perceptron (RMLP) with at least one hidden layer of fully or partially(More)
A method of training multilayer perceptrons (MLPs) to reach a global or nearly global minimum of the standard mean squared error (MSE) criterion is proposed. It has been found that the region in the weight space that does not have a local minimum of the normalized riskaverting error (NRAE) criterion expands strictly to the entire weight space as the(More)
A method of training neural networks using the risk-averting error (RAE) criterion J<sub>&#x03BB;</sub> (w), which was presented in IJCNN 2001, has the capability to avoid nonglobal local minima, but suffers from a severe limitation on the magnitude of the risk-sensitivity index &#x03BB;. To eliminating the limitation, an improved method using the(More)
Proper use of the normalized risk-averting error (NRAE) criterion has been shown to avoid nonglobal local minima effectively in the mean squared error (MSE) criterion. For training on large datasets, a pairwise algorithm for the NRAE criterion similar to the widely-used least mean square algorithm for the MSE criterion is proposed. The gradual(More)
The injection operator used by McKean to construct Brownian paths on a Lie group is employed to formulate a class of signal detection problems on matrix Lie groups. The hypotheses that the signal is absent and present in the observation on a Lie group are described by a pair of bilinear matrix Ito equations. The injection operator is shown to be almost(More)