tancik / fourier-feature-networks

Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains
https://people.eecs.berkeley.edu/~bmild/fourfeat/
MIT License
1.26k stars 134 forks source link

Parameters a_j and b_j #3

Open kwea123 opened 4 years ago

kwea123 commented 4 years ago

As discussed in A.3, training a and b does not seem to influence the performance. An intuition is as what you mentioned: "as the b_j values do not deviate significantly from their initial values" (How about a_j?). Do you have any theoretic evidence of why this is true? To my knowledge, in language processing tasks, they let the network learn also the embedding of each token, and it makes the performance better.

Is there a notebook to experiment with this (Figure 8)?