using a convolutional network for mechanistic interpretability
we use a convolutional network to predict the inputs and outputs of a separate target net
we use a convolutional network to predict the inputs and outputs of a separate target net
we use a historical example to illustrate a graphical tree approach to bayes' equation for updating beliefs in light of new evidence
we show how to use a convolutional net for the identify-handwritten-numbers task
we derive the backprop equations necessary for training a convolutional neural network
we present a to-do list game that combines foreign language learning, writing, and role playing