Stephen C. Ashmore

Learn More
We present a method for training a deep neural network containing sinusoidal activation functions to fit to time-series data. Weights are initialized using a fast Fourier transform, then trained with regular-ization to improve generalization. A simple dynamic parameter tuning method is employed to adjust both the learning rate and regularization term, such(More)
We present Forward Bipartite Alignment (FBA), a method that aligns the topological structures of two neural networks. Neural networks are considered to be a black box, because neural networks have a complex model surface determined by their weights that combine attributes non-linearly. Two networks that make similar predictions on training data may still(More)
  • 1