17 citations · 17 across the 1 of their papers we have counts for
3 papers
Takens-inspired neuromorphic processor: a downsizing tool for random recurrent neural networks via feature extraction
Bicky A. Marquez, Jose Suarez-Vargas, Bhavin J. Shastri
We describe a new technique which minimizes the amount of neurons in the hidden layer of a random recurrent neural network (rRNN) for time series prediction. Merging Takens-based a…
Digital Electronics and Analog Photonics for Convolutional Neural Networks (DEAP-CNNs)
Viraj Bangari, Bicky A. Marquez, Heidi B. Miller +6
Convolutional Neural Networks (CNNs) are powerful and highly ubiquitous tools for extracting features from large datasets for applications such as computer vision and natural langu…
Highly-complex optical signal generation using electro-optical systems with non-linear, non-invertible transmission functions
José J. Suárez-Vargas, Bicky A. Márquez, Jorge A. González
We present a scheme whereby a static non-linear, non-invertible transmission function performed by the electro-optic Mach-Zehnder modulator produces highly complex optical chaos. T…