Charlie Stross on Nostr: Paper: The boundary of neural network trainability is fractal "Some fractals – for ...
Paper: The boundary of neural network trainability is fractal
"Some fractals – for instance those associated with the Mandelbrot and quadratic Julia sets – are computed by iterating a function, and identifying the boundary between hyperparameters for which the resulting series diverges or remains bounded. Neural network training similarly involves iterating an update function …"
https://arxiv.org/html/2402.06184v1
"Some fractals – for instance those associated with the Mandelbrot and quadratic Julia sets – are computed by iterating a function, and identifying the boundary between hyperparameters for which the resulting series diverges or remains bounded. Neural network training similarly involves iterating an update function …"
https://arxiv.org/html/2402.06184v1