Explainable AI using brain-motivated neural networks
Feedforward networks have been the basis of Artificial Neural Networks such as Deep, Convolution, and Recurrent Networks. However the internal decision processes of feedforward networks are difficult to explain: they are known to be a "black-box". We have developed a new type of neural network motivated by neuroscience. This allows the network to be more updatable, and the internal decision process easier to understand. We are now able to convert feedforward networks to our form and explain their internal workings. We will demonstrate some of these benefits.
MD/PhD Neuroscience & Computer Science
|Your Review / Feedback :|
|Your Company :|