266,66 €
296,29 €
-10% with code: EXTRA
Recurrent Neural Networks for Temporal Data Processing
Recurrent Neural Networks for Temporal Data Processing
266,66
296,29 €
  • We will send in 10–14 business days.
The RNNs (Recurrent Neural Networks) are a general case of artificial neural networks where the connections are not feed-forward ones only. In RNNs, connections between units form directed cycles, providing an implicit internal memory. Those RNNs are adapted to problems dealing with signals evolving through time. Their internal memory gives them the ability to naturally take time into account. Valuable approximation results have been obtained for dynamical systems.
296.29
  • Publisher:
  • Year: 2011
  • Pages: 116
  • ISBN-10: 9533076852
  • ISBN-13: 9789533076850
  • Format: 17 x 24.4 x 0.8 cm, kieti viršeliai
  • Language: English
  • SAVE -10% with code: EXTRA

Recurrent Neural Networks for Temporal Data Processing (e-book) (used book) | bookbook.eu

Reviews

(4.00 Goodreads rating)

Description

The RNNs (Recurrent Neural Networks) are a general case of artificial neural networks where the connections are not feed-forward ones only. In RNNs, connections between units form directed cycles, providing an implicit internal memory. Those RNNs are adapted to problems dealing with signals evolving through time. Their internal memory gives them the ability to naturally take time into account. Valuable approximation results have been obtained for dynamical systems.

EXTRA 10 % discount with code: EXTRA

266,66
296,29 €
We will send in 10–14 business days.

The promotion ends in 22d.05:38:02

The discount code is valid when purchasing from 10 €. Discounts do not stack.

Log in and for this item
you will receive 2,96 Book Euros!?
  • Publisher:
  • Year: 2011
  • Pages: 116
  • ISBN-10: 9533076852
  • ISBN-13: 9789533076850
  • Format: 17 x 24.4 x 0.8 cm, kieti viršeliai
  • Language: English English

The RNNs (Recurrent Neural Networks) are a general case of artificial neural networks where the connections are not feed-forward ones only. In RNNs, connections between units form directed cycles, providing an implicit internal memory. Those RNNs are adapted to problems dealing with signals evolving through time. Their internal memory gives them the ability to naturally take time into account. Valuable approximation results have been obtained for dynamical systems.

Reviews

  • No reviews
0 customers have rated this item.
5
0%
4
0%
3
0%
2
0%
1
0%
(will not be displayed)