Statistiques
3 Questions
0 Réponses
RANG
199 351
of 300 750
RÉPUTATION
0
CONTRIBUTIONS
3 Questions
0 Réponses
ACCEPTATION DE VOS RÉPONSES
66.67%
VOTES REÇUS
2
RANG
of 21 073
RÉPUTATION
N/A
CLASSEMENT MOYEN
0.00
CONTRIBUTIONS
0 Fichier
TÉLÉCHARGEMENTS
0
ALL TIME TÉLÉCHARGEMENTS
0
RANG
of 170 837
CONTRIBUTIONS
0 Problèmes
0 Solutions
SCORE
0
NOMBRE DE BADGES
0
CONTRIBUTIONS
0 Publications
CONTRIBUTIONS
0 Public Chaîne
CLASSEMENT MOYEN
CONTRIBUTIONS
1 Point fort
NOMBRE MOYEN DE LIKES
0
Feeds
Discussion
feature request: better forward/backward pass functionalities for neural network operations
I'm working on training neural networks without backpropagation / automatic differentiation, using locally derived analytic form...
2 mois il y a | 0
Question
feature request: better forward/backward pass functionalities for neural network operations
I'm working on training neural networks without backpropagation / automatic differentiation, using locally derived analytic form...
2 mois il y a | 1 réponse | 0
0
réponseQuestion
making a custom way to train CNNs, and I am noticing that avgpool is SIGNIFICANTLY faster than maxpool in forward and backwards passes…
I’m designing a custom training procedure for a CNN that is different from backpropagation in that I use manual update rules for...
4 mois il y a | 2 réponses | 2
2
réponsesQuestion
need to vectorize efficiently calculating only certain values in the matrix multiplication A * B, using a logical array L the size of A * B
I have matrices A (m by v) and B (v by n). I also have a logical matrix L (m by n). I am interested in, as efficiently as possi...
10 mois il y a | 2 réponses | 0
