Link preview
Forward Self-Models Learn an Empirical Approximation of Neural Network Computation
Small networks trained to predict a neural network's later-layer activations from its earlier-layer activations, learning an empirical approximation of the computational function that the intervening layers implement. Jasper Gilley · jagilley.github.io
Small networks trained to predict a neural network's later-layer activations from its earlier-layer activations, learning an empirical approximation of the computational function that the intervening layers implement.
Comments