Recurrent neural network & feed forward network

1. RNN basics in deep learning
Prof. Neeraj Bhargava
Kapil Chauhan
Department of Computer Science
School of Engineering & Systems Sciences
MDS University, Ajmer

2. Introduction
 A Neural Network consists of different layers
connected to each other, working on the structure and
function of a human brain.
 It learns from huge volumes of data and uses complex
algorithms to train a neural net.

3. Recurrent Neural Network
 A Recurrent Neural Network works on the principle of
saving the output of a particular layer and feeding this
back to the input in order to predict the output of the
layer.

4. Simple Recurrent Neural Network

5. Recurrent Neural Network

6. Feed-Forward Neural Networks
 A feed-forward neural network allows information to
flow only in the forward direction, from the input
nodes, through the hidden layers, and to the output
nodes.
 There are no cycles or loops in the network.

7. Feed-forward Neural Network

8. Why Recurrent Neural Networks?
 Recurrent neural networks were created because there
were a few issues in the feed-forward neural network:
 Cannot handle sequential data.
 Considers only the current input.
 Cannot memorize previous inputs.

9. Applications of Recurrent Neural
Networks
 Image Captioning
 Time Series Prediction
 Natural Language Processing
 Machine Translation

10. Assignment
 Explain Recurrent Neural Networks in deep learning
with example.