1. Home
2. Premium
3. IEEE ICASSP 2020 Virtual Conference May 2020
4. Sndcnn: Self-Normalizing Deep Cnns With Scaled Exponential Linear Units For Speech Recognition

Sndcnn: Self-Normalizing Deep Cnns With Scaled Exponential Linear Units For Speech Recognition

Collection:

IEEE ICASSP 2020 Virtual Conference May 2020

Very deep CNNs achieve state-of-the-art results in both computer vision and speech recognition, but are difficult to train. The most popular way to train very deep CNNs is to use shortcut connec- tions (SC) together with batch normalization (BN). Inspired

• IEEE MemberUS $11.00
• Society MemberUS $0.00
• IEEE Student MemberUS $11.00
• Non-IEEE MemberUS $15.00

Purchase

Videos in this product

Sndcnn: Self-Normalizing Deep Cnns With Scaled Exponential Linear Units For Speech Recognition

00:14:45

0 views

Very deep CNNs achieve state-of-the-art results in both computer vision and speech recognition, but are difficult to train. The most popular way to train very deep CNNs is to use shortcut connec- tions (SC) together with batch normalization (BN). Inspired