A

Seminar Report
On
Deep learning

Submitted in partial fulfillment of the requirement for the degree of

Bachelor of Information Technology VI Semester

Session: (2019-2020)

GUIDIED BY: SUBMITTED BY:

Dr. PRAVEEN SAINI kavita bhatt
ASSOCIATE PROFESSOR shivani Basoor
UIM B.Sc(IT) 6th Sem
 CERTIFICATE

This is to certify that the seminar/presentation report on the topic “deep learning ” has
been studied and presented by Kavita bhatt and shivani basoor in partial fulfillment of their
degree of Master of Computer Application, Uttaranchal Institute of Management ,UU.

This seminar/presentation report has been found satisfactory and is approved for submission.

Dated: Guide Name:- Dr. Praveen Saini

Designation: - Associate Professor
 ACKNOWLEDGEMENT

The most awaited moment of any endeavour is successful completion, but nothing can be
successful if done alone. Success is the outcome of contribution and consistent help of various
persons and we thank those who helped us in successful completion of this report.
First and foremost, We would like to thank Dr. Pradeep Suri, Director of UIM for providing
such a healthy and encouraging environment to study in.
We are profusely thankful to the Head of department of computer science and application, Dr.
Sonal Sharma, and Dr. Praveen Saini, Associate Professor he has been generous enough to
provide us an opportunity and accepting our candidature for the most valuable guidance and
affordable treatment given to us at every stage to boost our morale.

Name: - Kavita bhatt

Course: - B.Sc(IT) 6th Sem

Roll. No.:- 31

Name: - shivani Basoor

Course: - B.Sc(IT) 6th Sem

Roll. No.:- 47
 CONTENTS

1. Abstract………………………………………………………….………………..…1
2. Introduction……………….…………………………………………………..……..2
3. Objectives…………………………………………………………………………....3
4. How it works………………………………………………………………………...4
5. Architecture of deep learning ……………………....…….………………………...5
5.1 .Recurrent neural networks.....................................................6
6. Applications…………………….……………………………………..…………......7
7. References…………………………………………………………………………...8
1. ABSTRACT

Deep learning is an emerging area of machine learning (ML) research. It comprises multiple
hidden layers of artificial neural networks. The deep learning methodology applies nonlinear
transformations and model abstractions of high level in large databases.

The recent advancements in deep learning architec-tures within numerous fields have already
provided significant contributions in artificial intelligence.
2. INTRODUCTION
Deep learning is a machine learning technique that teaches computers to do what comes
naturally to humans: learn by example. Deep learning is a key technology behind driverless
cars, enabling them to recognize a stop sign, or to distinguish a pedestrian from a lamppost. It
is the key to voice control in consumer devices like phones, tablets, TVs, and hands-free
speakers. Deep learning is getting lots of attention lately and for good reason. It’s achieving
results that were not possible before.

ln deep learning, a computer model learns to perform classification tasks directly from images,
text, or sound. Deep learning models can achieve state-of-the-art accuracy, sometimes
exceeding human-level performance. Models are trained by using a large set of labeled data
and neural network architectures that contain many layers.
3. OBJECTIVES
Gain in-depth knowledge of TensorFlow along with its functions, operations, and the
execution pipeline.

Implement linear regression and gradient descent in TensorFlow.

Understand the concept of artificial neural networks, convolutional neural networks, and
recurrent neural networks.

Discuss how to speed up neural networks along with regularization techniques to reduce
overfitting.

Implement deep learning algorithms, and learn how to train deep networks.
4. HOW IT WORKS
Deep Learning uses a Neural Network to imitate animal intelligence. There are three types of
layers of neurons in a neural network: the Input Layer, the Hidden Layer(s), and the Output
Layer. Connections between neurons are associated with a weight, dictating the importance of
the input value.

Most deep learning methods use neural network architectures, which is why deep learning
models are often referred to as deep neural networks.

The term “deep” usually refers to the number of hidden layers in the neural network.
Traditional neural networks only contain 2-3 hidden layers, while deep networks can have as
many as 150.
5. ARCHITECTURE OF DEEP LEARNING
These architectures are applied in a wide range of scenarios, but the following table lists some
of their typical applications.

ArchitectureApplicationRNNSpeech recognition, handwriting recognitionLSTM/GRU

networksNatural language text compression, handwriting recognition, speech recognition,
gesture recognition, image captioningCNNImage recognition, video analysis, natural language
processingDBNImage recognition, information retrieval, natural language understanding,
failure predictionDSNInformation retrieval, continuous speech recognition.

Recurrent neural networks

The RNN is one of the foundational network architectures from which other deep learning
architectures are built. The primary difference between a typical multilayer network and a
recurrent network is that rather than completely feed-forward connections, a recurrent network
might have connections that feed back into prior layers (or into the same layer). This feedback
allows RNNs to maintain memory of past inputs and model problems in time.

RNNs consist of a rich set of architectures (we’ll look at one popular topology called LSTM
next). The key differentiator is feedback within the network, which could manifest itself from
a hidden layer, the output layer, or some combination thereof.
6.APPLICATION
1.Colorization of Black and White Images.

2.Adding Sounds To Silent Movies.

3.Automatic Machine Translation.

4.Object Classification in Photographs.

5.Automatic Handwriting Generation.

6.Character Text Generation.

7.Image Caption Generation.

8.Automatic Game Playing.

 7.REFERENCES
Bengio, Y., LeCun, Y., Hinton, G. ... Goodfellow, I., Bengio, Y. and Courville, A.
(2016) Deep Learning.

WEB URLS:

 https://www.google.com/
 https://en.wikipedia.org/
 https://www.tutorialspoint.com/