Tanh
دالة الظل الزائدي
دالة تنشيط تحول مخرجات العصبونات إلى نطاق متوازن محصور بين -1 و1.
Tanh
Also translated asدالة تانش التنشيطية، دالة جيب التمام الزائدية المعدلة
First appears in this corpus in: Learning Long-Term Dependencies with Gradient Descent is Difficult (1994)
Appears in these papers
- ImageNet Classification with Deep Convolutional Neural Networks2012in the sky ✦
- A General Reinforcement Learning Algorithm That Masters Chess, Shogi, and Go Through Self-Play2018in the sky ✦
- Learning Long-Term Dependencies with Gradient Descent is Difficult1994in the sky ✦
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks2015in the sky ✦
- Deep Learning2015in the sky ✦
- Gaussian Error Linear Units (GELUs)2016in the sky ✦
- Highway Networks2015in the sky ✦
- Recurrent Neural Networks (RNNs): A Gentle Introduction and Overview2019in the sky ✦
- Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor2018in the sky ✦
- Understanding the Difficulty of Training Deep Feedforward Neural Networks2010in the sky ✦
- Understanding the Difficulty of Training Deep Feedforward Neural Networks2010in the sky ✦