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.
Sheet Pile Wall Design and Construction: A Practical Guide for Civil Engineer...
RNN Seminar on Predicting Words with Recurrent Neural Networks
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
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
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