This document provides an overview of deep learning including definitions, architectures, types of deep learning networks, and applications. It defines deep learning as a branch of machine learning that uses neural networks with multiple hidden layers to perform feature extraction and transformation without being explicitly programmed. The main architectures discussed are deep neural networks, deep belief networks, and recurrent neural networks. The types of deep learning networks covered include feedforward neural networks, recurrent neural networks, convolutional neural networks, restricted Boltzmann machines, and autoencoders. Finally, the document discusses several applications of deep learning across industries such as self-driving cars, natural language processing, virtual assistants, and healthcare.

1. DEEP LEARNING
Seminar Report

2. CHAPTER 1
INTRODUCTION
1.1 DEEP LEARNING
Deep learning is based on the branch of machine learning, which is a
subset of artificial intelligence. Since neural networks imitate the human
brain and so deep learning will do. In deep learning, nothing is
programmed explicitly. Basically, it is a machine learning class that
makes use of numerous nonlinear processing units so as to perform
feature extraction as well as transformation. The output from each
preceding layer is taken as input by each one of the successive layers.
Deep learning is a collection of statistical techniques of machine
learning for learning feature hierarchies that are actually based on
artificial neural networks.
So basically, deep learning is implemented by the help of deep networks,
which are nothing but neural networks with multiple hidden layers.
FIG 1DEEP LEARNING
How deep learning is a subset of machine learning and how machine
learning is a subset of artificial intelligence (AI).

3. 1.2 ARCHITECTURES
o Deep Neural Networks
It is a neural network that incorporates the complexity of a certain
level, which means several numbers of hidden layers are
encompassed in between the input and output layers. They are
highly proficient on model and process non-linear associations.
o Deep Belief Networks
A deep belief network is a class of Deep Neural Network that
comprises of multi-layer belief networks.
Steps to perform DBN:
1. With the help of the Contrastive Divergence algorithm, a
layer of features is learned from perceptible units.
2. Next, the formerly trained features are treated as visible units,
which perform learning of features.
3. Lastly, when the learning of the final hidden layer is
accomplished, then the whole DBN is trained.
o Recurrent Neural Networks
It permits parallel as well as sequential computation, and it is
exactly similar to that of the human brain (large feedback network
of connected neurons). Since they are capable enough to reminisce
all of the imperative things related to the input they have received,
so they are more precise.

4. CHAPTER 2
TYPES OF DEEP LEARNING NETWORKS
FIG 2 TYPES OF DEEP LEARNING NETWORKS
2.1. Feed Forward Neural Network
A feed-forward neural network is none other than an Artificial Neural
Network, which ensures that the nodes do not form a cycle. In this kind
of neural network, all the perceptrons are organized within layers, such
that the input layer takes the input, and the output layer generates the
output. Since the hidden layers do not link with the outside world, it is
named as hidden layers. Each of the perceptrons contained in one single
layer is associated with each node in the subsequent layer. It can be
concluded that all of the nodes are fully connected. It does not contain
any visible or invisible connection between the nodes in the same layer.
There are no back-loops in the feed-forward network. To minimize the
prediction error, the backpropagation algorithm can be used to update
the weight values.
Applications:
o Data Compression

5. o Pattern Recognition
o Computer Vision
o Sonar Target Recognition
o Speech Recognition
o Handwritten Characters Recognition
2.2. Recurrent Neural Network
Recurrent neural networks are yet another variation of feed-forward
networks. Here each of the neurons present in the hidden layers receives
an input with a specific delay in time. The Recurrent neural network
mainly accesses the preceding info of existing iterations. For example, to
guess the succeeding word in any sentence, one must have knowledge
about the words that were previously used. It not only processes the
inputs but also shares the length as well as weights crossways time. It
does not let the size of the model to increase with the increase in the
input size. However, the only problem with this recurrent neural network
is that it has slow computational speed as well as it does not contemplate
any future input for the current state. It has a problem with reminiscing
prior information.
Applications:
o Machine Translation
o Robot Control
o Time Series Prediction
o Speech Recognition
o Speech Synthesis
o Time Series Anomaly Detection
o Rhythm Learning
o Music Composition
2 .3. Convolutional Neural Network

6. Convolutional Neural Networks are a special kind of neural network
mainly used for image classification, clustering of images and object
recognition. DNNs enable unsupervised construction of hierarchical
image representations. To achieve the best accuracy, deep convolutional
neural networks are preferred more than any other neural network.
Applications:
o Identify Faces, Street Signs, Tumors.
o Image Recognition.
o Video Analysis.
o NLP.
o Anomaly Detection.
o Drug Discovery.
o Checkers Game.
o Time Series Forecasting.
2.4. Restricted Boltzmann Machine
RBMs are yet another variant of Boltzmann Machines. Here the neurons
present in the input layer and the hidden layer encompasses symmetric
connections amid them. However, there is no internal association within
the respective layer. But in contrast to RBM, Boltzmann machines do
encompass internal connections inside the hidden layer. These
restrictions in BMs helps the model to train efficiently.
Applications:
o Filtering.
o Feature Learning.
o Classification.
o Risk Detection.
o Business and Economic analysis.

7. 2.5. Autoencoders
An autoencoder neural network is another kind of unsupervised machine
learning algorithm. Here the number of hidden cells is merely small than
that of the input cells. But the number of input cells is equivalent to the
number of output cells. An autoencoder network is trained to display the
output similar to the fed input to force AEs to find common patterns and
generalize the data. The autoencoders are mainly used for the smaller
representation of the input. It helps in the reconstruction of the original
data from compressed data. This algorithm is comparatively simple as it
only necessitates the output identical to the input.
o Encoder: Convert input data in lower dimensions.
o Decoder: Reconstruct the compressed data.
Applications:
o Classification.
o Clustering.
o Feature Compression.

8. CHAPTER 3
Top Applications of Deep Learning Across Industries
1. Self Driving Cars
2. News Aggregation and Fraud News Detection
3. Natural Language Processing
4. Virtual Assistants
5. Entertainment
6. Visual Recognition
7. Fraud Detection
8. Healthcare
9. Personalisations
10. Detecting Developmental Delay in Children
11. Colourisation of Black and White images
12. Adding sounds to silent movies
13. Automatic Machine Translation
14. Automatic Handwriting Generation
15. Automatic Game Playing
16. Language Translations
17. Pixel Restoration
18. Photo Descriptions
19. Demographic and Election Predictions
20. Deep Dreaming

9. FIG 3 Top Applications of Deep Learning Across Industries

10. FIG 4 PYTHON APPLICATIONS

11. FIG 5 APPLICATIONS OF AI
FIG 6 DEEP LEARNING APPLIKCATIONS OF AI

12. FIG 7 CHATBOT USES

13. 3.1 CHATBOT
FIG 8 CHATBOT BENIFITS
FIG 9 APPLICATIONS

14. A chatbot is a software application used to conduct an on-line
chat conversation via text or text-to-speech, in lieu of providing direct
contact with a live human agent.[1]
A chatbot is a type of software that
can automate conversations and interact with people through messaging
platforms. Designed to convincingly simulate the way a human would
behave as a conversational partner, chatbot systems typically require
continuous tuning and testing, and many in production remain unable to
adequately converse or pass the industry standard Turing test.[
The term
"ChatterBot" was originally coined by Michael Mauldin (creator of the
first Verbot) in 1994 to describe these conversational programs.
Chatbots are used in dialog systems for various purposes including
customer service, request routing, or information gathering. While some
chatbot applications use extensive word-classification processes, natural
language processors, and sophisticated AI, others simply scan for
general keywords and generate responses using common phrases
obtained from an associated library or database.
Most chatbots are accessed on-line via website popups or through virtual
assistants. They can be classified into usage categories that
include: commerce (e-commerce via
chat), education, entertainment, finance, health, news, and productivity.
CHATBOT SEQUENCES
Used by marketers to script sequences of messages, very similar to
an Autoresponder sequence. Such sequences can be triggered by user
opt-in or the use of keywords within user interactions. After a trigger
occurs a sequence of messages is delivered until the next anticipated
user response. Each user response is used in the decision tree to help the
chatbot navigate the response sequences to deliver the correct response
message.
CUSTOMER SERVICE
Many high-tech banking organizations are looking to integrate
automated AI-based solutions such as chatbots into their customer
service in order to provide faster and cheaper assistance to their clients

15. who are becoming increasingly comfortable with technology. In
particular, chatbots can efficiently conduct a dialogue, usually replacing
other communication tools such as email, phone, or SMS. In banking,
their major application is related to quick customer service answering
common requests, as well as transactional support.
LIMITATIONS OF CHATBOTS
The creation and implementation of chatbots is still a developing area,
heavily related to artificial intelligence and machine learning, so the
provided solutions, while possessing obvious advantages, have some
important limitations in terms of functionalities and use cases. However,
this is changing over time.
The most common ones are listed below:
• As the database, used for output generation, is fixed and limited,
chatbots can fail while dealing with an unsaved query.[45]
• A chatbot's efficiency highly depends on language processing and is
limited because of irregularities, such as accents and mistakes.
• Chatbots are unable to deal with multiple questions at the same time
and so conversation opportunities are limited.
• Chatbots require a large amount of conversational data to train.
• Chatbots have difficulty managing non-linear conversations that must
go back and forth on a topic with a user
• As it happens usually with technology-led changes in existing
services, some consumers, more often than not from the old
generation, are uncomfortable with chatbots due to their limited
understanding, making it obvious that their requests are being dealt
with by machines.

16. 3.2 SPEECH RECOGNITION
Speech recognition is an interdisciplinary subfield of computer
science and computational linguistics that develops methodologies and
technologies that enable the recognition and translation of spoken
language into text by computers. It is also known as automatic speech
recognition (ASR), computer speech recognition or speech to text (STT).
It incorporates knowledge and research in the computer
science, linguistics and computer engineering fields.
Speech recognition applications include voice user interfaces such as
voice dialing (e.g. "call home"), call routing,etc.
FIG 10
In-car systems
Typically a manual control input, for example by means of a finger
control on the steering-wheel, enables the speech recognition system and
this is signalled to the driver by an audio prompt. Following the audio
prompt, the system has a "listening window" during which it may accept
a speech input for recognition.
Simple voice commands may be used to initiate phone calls, select radio
stations or play music from a compatible smartphone, MP3 player or
music-loaded flash drive. Voice recognition capabilities vary between
car make and model. Some of the most recent[
car models offer natural-
language speech recognition in place of a fixed set of commands,
allowing the driver to use full sentences and common phrases. With such

17. systems there is, therefore, no need for the user to memorize a set of
fixed command words.
Usage in education and daily life
For language learning, speech recognition can be useful for learning
a second language. It can teach proper pronunciation, in addition to
helping a person develop fluency with their speaking skills
Students who are blind (see Blindness and education) or have very low
vision can benefit from using the technology to convey words and then
hear the computer recite them, as well as use a computer by
commanding with their voice, instead of having to look at the screen and
keyboard.
Students who are physically disabled or suffer from Repetitive strain
injury/other injuries to the upper extremities can be relieved from having
to worry about handwriting, typing, or working with scribe on school
assignments by using speech-to-text programs. They can also utilize
speech recognition technology to freely enjoy searching the Internet or
using a computer at home without having to physically operate a mouse
and keyboard.
Speech recognition can allow students with learning disabilities to
become better writers. By saying the words aloud, they can increase the
fluidity of their writing, and be alleviated of concerns regarding spelling,
punctuation, and other mechanics of writing.[95]
Also, see Learning
disability.
Use of voice recognition software, in conjunction with a digital audio
recorder and a personal computer running word-processing software has
proven to be positive for restoring damaged short-term-memory
capacity, in stroke and craniotomy individuals.
SECURITY CONCERNS
Speech recognition can become a means of attack, theft, or accidental
operation. For example, activation words like "Alexa" spoken in an
audio or video broadcast can cause devices in homes and offices to start
listening for input inappropriately, or possibly take an unwanted

18. action.[108]
Voice-controlled devices are also accessible to visitors to the
building, or even those outside the building if they can be heard inside.
Attackers may be able to gain access to personal information, like
calendar, address book contents, private messages, and documents. They
may also be able to impersonate the user to send messages or make
online purchases.
Two attacks have been demonstrated that use artificial sounds. One
transmits ultrasound and attempt to send commands without nearby
people noticing. The other adds small, inaudible distortions to other
speech or music that are specially crafted to confuse the specific speech
recognition system into recognizing music as speech, or to make what
sounds like one command to a human sound like a different command to
the system
3.3 PATTERN RECOGNITION
Pattern recognition is the automated recognition of patterns and
regularities in data. It has applications in statistical data analysis, signal
processing, image analysis, information retrieval, bioinformatics, data
compression, computer graphics and machine learning. Pattern
recognition has its origins in statistics and engineering; some modern
approaches to pattern recognition include the use of machine learning,
due to the increased availability of big data and a new abundance
of processing power. However, these activities can be viewed as two
facets of the same field of application, and together they have undergone
substantial development over the past few decades. A modern definition
of pattern recognition is:
The field of pattern recognition is concerned with the automatic
discovery of regularities in data through the use of computer algorithms
and with the use of these regularities to take actions such as classifying
the data into different categories

19. Uses
FIG 11 The face was automatically detected by special software.
Within medical science, pattern recognition is the basis for computer-
aided diagnosis (CAD) systems. CAD describes a procedure that
supports the doctor's interpretations and findings. Other typical
applications of pattern recognition techniques are automatic speech
recognition, speaker identification, classification of text into several
categories (e.g., spam/non-spam email messages), the automatic
recognition of handwriting on postal envelopes, automatic recognition of
images of human faces, or handwriting image extraction from medical
forms. The last two examples form the subtopic image analysis of
pattern recognition that deals with digital images as input to pattern
recognition systems
Optical character recognition is a classic example of the application of a
pattern classifier, see OCR-example. The method of signing one's name
was captured with stylus and overlay starting in 1990. The strokes,
speed, relative min, relative max, acceleration and pressure is used to
uniquely identify and confirm identity. Banks were first offered this
technology, but were content to collect from the FDIC for any bank
fraud and did not want to inconvenience customers.
Pattern recognition has many real-world applications in image
processing, some examples include:
• Identification And Authentication: e.g., license plate
recognition, fingerprint analysis, face detection/verification;, and
voice-based authentication.

20. • Medical Diagnosis: e.g., screening for cervical cancer (Papnet)
breast tumors or heart sounds;
• Defence: various navigation and guidance systems, target recognition
systems, shape recognition technology etc.
• Mobility: advanced driver assistance systems, autonomous vehicle
technology, etc.
In psychology, pattern recognition (making sense of and identifying
objects) is closely related to perception, which explains how the sensory
inputs humans receive are made meaningful. Pattern recognition can be
thought of in two different ways: the first being template matching and
the second being feature detection. A template is a pattern used to
produce items of the same proportions. The template-matching
hypothesis suggests that incoming stimuli are compared with templates
in the long-term memory. If there is a match, the stimulus is identified.
Feature detection models, such as the Pandemonium system for
classifying letters (Selfridge, 1959), suggest that the stimuli are broken
down into their component parts for identification. For example, a
capital E has three horizontal lines and one vertical line.
3.4 NEURAL MACHINE TRANSLATION
Neural machine translation (NMT) is an approach to machine
translation that uses an artificial neural network to predict the likelihood
of a sequence of words, typically modeling entire sentences in a single
integrated model.

21. Fig 12 Neural Machine Translations
NMT departs from phrase-based statistical approaches that use
separately engineered subcomponents Neural machine translation
(NMT) is not a drastic step beyond what has been traditionally done in
statistical machine translation (SMT). Its main departure is the use of
vector representations ("embeddings", "continuous space
representations") for words and internal states. The structure of the
models is simpler than phrase-based models. There is no separate
language model, translation model, and reordering model, but just a
single sequence model that predicts one word at a time. However, this
sequence prediction is conditioned on the entire source sentence and the
entire already produced target sequence. NMT models use deep
learning and representation learning.
The word sequence modeling was at first typically done using
a recurrent neural network (RNN). A bidirectional recurrent neural
network, known as an encoder, is used by the neural network to encode
a source sentence for a second RNN, known as a decoder, that is used to
predict words in the target language. Recurrent neural networks face
difficulties in encoding long inputs into a single vector. This can be
compensated by an attention mechanism which allows the decoder to
focus on different parts of the input while generating each word of the

22. output. There are further Coverage Models addressing the issues in such
attention mechanisms, such as ignoring of past alignment information
leading to over-translation and under-translation.
Convolutional Neural Networks (Convnets) are in principle somewhat
better for long continuous sequences, but were initially not used due to
several weaknesses. These were successfully compensated for in 2017
by using "attention mechanisms".
An attention-based model, the transformer architecture remains the
dominant architecture for several language pairs.
3.5 MARKETING RESEARCH
Marketing research is the systematic gathering, recording, and analysis
of qualitative and quantitative data about issues relating
to marketing products and services. The goal is to identify and assess
how changing elements of the marketing mix impacts customer
behavior.
FIG 13 MARKET RESEARCH

23. FIG 14 RESEARCH PROCESS
Marketing research is often partitioned into two sets of categorical pairs,
either by target market:
• Consumer marketing research, (B2C) and
• Business-to-business (B2B) marketing research.
Or, alternatively, by methodological approach:
• Qualitative marketing research, and
• Quantitative marketing research.

24. Four common types of market research techniques include
surveys, interviews, focus groups, and customer observation.
• Surveys: the most commonly used.
• Interviews: the most insightful.
• Focus groups: the most dangerous.
• Observation: the most powerful.
• Create simple user personas.
• Conduct observational research.
7 Stages or Steps Involved in Marketing Research Process
• Identification and Defining the Problem: ...
• Statement of Research Objectives: ...
• Planning the Research Design or Designing the Research Study: ...
• Planning the Sample: ...
• Data Collection: ...
• Data Processing and Analysis: ...
• Formulating Conclusion, Preparing and Presenting the Report
the pros and cons of marketing?
• Advantage: Promotes Your Business to a Target Audience. ...
• Advantage: Helps You Understand Your Customers. ...
• Advantage: Helps Brand Your Business. ...
• Disadvantage: Costs of Marketing. ...
• Disadvantage: Time and Effort May Not Yield a Return.

25. CHAPTER 4
ADVANTAGES AND DISADVANTAGES
FIG 15 PRONS AND CONS
4.1 Limitations
o It only learns through the observations.
o It comprises of biases issues.
4.2 Advantages
o It lessens the need for feature engineering.
o It eradicates all those costs that are needless.
o It easily identifies difficult defects.
o It results in the best-in-class performance on problems.

26. 4.3 Disadvantages
o It requires an ample amount of data.
o It is quite expensive to train.
o It does not have strong theoretical groundwork.
4.4 CONCLUSION
Every time I see a new app, it is easy to imagine how recommendation
engines, sentiment analysis, image recognition, and chatbots could
improve the functionality of the app. All of these applications have been
made possible or greatly improved due to the power of Deep Learning.
Obviously, this is just my opinion and there are many more applications
of Deep Learning. However, I think this is a great list of applications that
have tons of tutorials and documentation and generally perform reliably.
In contrast to something like Generative Adversarial Nets or
Reinforcement Learning which are quite tricky to figure out how to
integrate into your web or mobile app. I think that these use cases of
Deep Learning have a universal applicability to most apps. Additionally,
Deep Learning is a subset of Data Science and there are many more ways
that Data Science can provide value to your software projects
4.5 REFERENCES
1. https://www.mygreatlearning.com/blog/deep-learning-applications/
2. https://en.wikipedia.org/wiki/Deep_learning