דלג לתוכן (מקש קיצור 's')
Logo of Technion
Logo of CS Department
אירועים

אירועים

Theory Seminar: On Symmetry and Initialization for Neural Network
event speaker icon
עידו נחום (מתמטיקה, טכניון)
event date icon
יום רביעי, 12.6.2019, 12:30
event location icon
טאוב 201
This work provides an additional step in the theoretical understanding of neural networks. We consider neural networks with one hidden layer and show that when learning symmetric functions, one can choose initial conditions so that standard SGD training efficiently produces generalization guarantees. We empirically verify this and show that this does not hold when the initial conditions are chosen at random. The proof of convergence investigates the interaction between the two layers of the network. Our results highlight the importance of using symmetry in the design of neural networks.
[בחזרה לאינדקס האירועים]