Postersland
Exploding and vanishing gradients in deep neural networks: the effect of residual connections
One-line summary
A robotics research paper on Exploding and vanishing gradients in deep neural networks: the effect of residual connections.
Engineering notes
Engineering notes will be added by the Robot Papers editorial team.
Chinese explanation / 中文解读
中文解读待补充：本站会优先为 VLA、具身智能、人形机器人控制、机器人操作等高价值论文补充中文说明。
Original abstract
The well known phenomenon of exploding and vanishing gradients in deep neural networks is analyzed using multiplicative ergodic theory. The effect of adding a residual connection is explained in this context. Specifically, a characterization of Liapunov exponents due to Furstenberg and Kifer is exploited in order to make a precise statement about the Liapunov spectrum and the effect of residual connections on it.
Links and sources
Looking for custom poster printing?
Postersland offers custom poster printing, bulk orders and personalized art prints for home, office, events and gifts.
View custom printing services
Comments