Looking Inside the Blackbox Anatomies of Real and Imaginary Neural Networks

The ‘Real’ portion is represented by exploiting Striatal Beat Frequencies in an EEG with the patented Single-Period Single-Frequency (SPSF) method and the ‘Imaginary’ is represented by a convolutional neural network transformed into bi-directional associative memory matrices. We demonstrated that we could interconnect, i.e., bridge, the intermediate layers of two broken CNNs both of which were trained for object detection and still make a good prediction. In this work we will use a dual sensory CNN implementation of speech and object detection and we will incorporate Neural Decoding into the EEG SPSF method to emulate how to circumvent the broken neural networks in a human-computer interface situation.

Reference: https://www.spiedigitallibrary.org/conference-proceedings-of-spie/13058/130580E/Circumventing-broken-neural-networks-both-real-and-imaginary-through-SPSF/10.1117/12.3014016.short

Speaker:

Dr. James LaRue has been a scientist/consultant for over 20 years. He has multiple publications. He earned his PhD in Engineering/Applied Science from University of New Orleans in 2003. He got his Masters in Math from Tulane University in 1995. He got his BA in Math/Education in 1992.But it all started out with an AAS in Instrumentation Electronics Technology at Monroe Community College, Rochester, NY in 1979.

The Zoom registration form will be provided no later than 1 hour prior the start time.

Live stream and recording link will be emailed to registered participants.