flâneur

Vallabh

0 followers · 5 following · 597 views

on the atlas — 12

highlights — 3

  • The last quantity you might want to track is the ratio of the update magnitudes to the value magnitudes. Note: updates, not the raw gradients (e.g. in vanilla sgd this would be the gradient multiplied by the learning rate). You might want to evaluate and track this ratio for every set of parameters independently. A rough heuristic is that this ratio should be somewhere around 1e-3. If it is lower than this then the learning rate might be too low. If it is higher then the learning rate is likely too high
    CS231n Convolutional Neural Networks for Visual Recognition
  • @add_to_class(A) def do(self): print('Class attribute "b" is', self.b) a.do()
    3.2. Object-Oriented Design for Implementation — Dive into Deep Learning 1.0.3 documentation
  • The town of Kundgol, which is in the neighboring Dharwar district, was a non-contiguous part of Jamkhandi State until it merged into the Indian Union on 19 February 1948.
    Jamakhandi - Wikipedia