This document outlines a seminar presentation on recurrent neural networks (RNNs). It introduces RNNs and discusses their applications. RNNs are able to use information from previous time steps to process sequential data like text or time series. Popular applications of RNNs mentioned include Google's autocomplete feature, machine translation, image captioning, and financial market prediction. The document outlines different RNN architectures like vanilla RNNs, long short-term memory networks, and gated recurrent units.

1. School of Engineering & Technology
Department of Computer Science & Engineering
Seminar Presentation on
Recurrent Neural Network
Submitted To:
Mr. Vaibhav Jain
Asst. Prof. & Program Leader
Dept. of CSE,
JLU-SOET
Submitted By:
Ashu
(2017BTCS006)

2. Outlines
 Introduction to RNN
 What is a Neural Network
 Popular Neural Networks
 Feed Forward Neural Network
 Why Recurrent Neural Network
 Applications of RNN
 What is a Recurrent Neural Network
 How does a RNN look like
 Types of Recurrent Neural Network
5/4/2021 2

3. Introduction to RNN
 Do you know how google’s autocomplete feature predicts
the rest of the words a user is typing?
5/4/2021 3

4. Introduction to RNN
 Do you know how google’s autocomplete feature predicts
the rest of the words a user is typing?
5/4/2021 4

5. Introduction to RNN
 Do you know how google’s autocomplete feature predicts
the rest of the words a user is typing?
5/4/2021 5

6. Introduction to RNN
 Do you know how google’s autocomplete feature predicts
the rest of the words a user is typing?
5/4/2021 6

7. What is a Neural Network
 Neural Networks used in Deep Learning, consists of
different layers connected to each other and work on the
structure and functions of a human brain. It learns from
huge volumes of data and uses complex algorithms to train
a neural net.
5/4/2021 7

8. What is a Neural Network
 Neural Networks used in Deep Learning, consists of
different layers connected to each other and work on the
structure and functions of a human brain. It learns from
huge volumes of data and uses complex algorithms to train
a neural net.
5/4/2021 8

9. Popular Neural Networks
5/4/2021 9

10. Feed Forward Neural Network
 In a Feed-Forward Network, information flows only in
forward direction, from the input nodes, through the hidden
layers (if any) and to the output nodes.There are no cycles
or loops in the network.
5/4/2021 10

11. Why Recurrent Neural Network
 Issues in Feed Forward Neural Network
5/4/2021 11

12. Why Recurrent Neural Network
 Solutions to Feed Forward Neural Network.
5/4/2021 12

13. Applications of RNN
5/4/2021 13

14. Applications of RNN
5/4/2021 14

15. Applications of RNN
5/4/2021 15

16. Applications of RNN
5/4/2021 16

17. Applications of RNN
5/4/2021 17

18. What is a Recurrent Neural
Network
 Recurrent Neural Network works on the principle of
saving the output of a layer and feedingthis back to the
input in order to predict the output of the layer.
5/4/2021 18

19. How does a RNN look like
5/4/2021 19

20. How does a RNN look like
5/4/2021 20

21. Types of Recurrent Neural
Network
5/4/2021 21

22. Types of Recurrent Neural
Network
5/4/2021 22

23. Types of Recurrent Neural
Network
5/4/2021 23

24. Types of Recurrent Neural
Network
5/4/2021 24

25. Thankyou!!!
5/4/2021 25