RNN: holding the sequence in memory, and the horizon of that memory
The same weights are applied again at every step and a state is carried forward. The memory is real, and its horizon is measurable too.
4 steps
175 XP
A free account is needed
Start the lesson →
Sources
- Elman, J. L. 1990 · Finding Structure in Time · Cognitive Science 14(2)
- Bengio, Y., Simard, P. & Frasconi, P. 1994 · Learning Long-Term Dependencies with Gradient Descent is Difficult · IEEE Trans. Neural Networks 5(2)
- Goodfellow, I., Bengio, Y. & Courville, A. 2016 · Deep Learning, Bölüm 10 · MIT Press
ML Academy · an interactive machine learning course that runs in your browser ·
All lessons