Introduction to deep Learning:

 Deep Learning is a subset of Machine Learning that is based on artificial neural

networks (ANNs) with multiple layers, also known as deep neural networks (DNNs).
 These neural networks are inspired by the structure and function of the human
brain, and they are designed to learn from large amounts of data in an
unsupervised or semi-supervised manner.

 Deep Learning models can automatically learn features from the data, which
makes them well-suited for tasks such as image recognition, speech
recognition, and natural language processing. The most widely used
architectures in deep learning are feedforward neural networks,
convolutional neural networks (CNN’s), and recurrent neural networks
(RNNs).

Feed-Forward neural network (FNN’s):

 Feedforward neural networks (FNNs) are the simplest type of ANN, with a linear
flow of information through the network. FNNs have been widely used for tasks
such as image classification, speech recognition, and natural language processing .

Convolutional Neural Networks (CNNs) :

 Convolutional Neural Networks (CNNs) are a special type of FNNs designed
specifically for image and video recognition tasks. CNNs can automatically learn
features from the images, which makes them well-suited for tasks such as image
classification, object detection.

Recurrent Neural Networks (RNNs) :

 Recurrent Neural Networks (RNNs) are a type of neural networks that are able to
process sequential data, such as time series and natural language which makes
them well-suited for tasks such as speech recognition, natural language
processing, and language translation .

Important:
 Deep Learning models are trained using large amounts of labelled data and require
significant computational resources. With the increasing availability of large
amounts of data and computational resources, deep learning has been able to
achieve state-of-the-art performance in a wide range of applications such as image
and speech recognition, natural language processing, and more.

Difference between machine learning and deep learning:

Machine Learning
Works on small amount of Dataset for
accuracy.
Dependent on Low-end Machine.
Divides the tasks into sub-tasks, solves
them individually and finally combine the
results.
Takes less time to train.
Testing time may increase.
Deep learning
Works on Large amount of Dataset .
Heavily dependent on High-end Machine.
Solves problem end to end.
Takes longer time to train.
Less time to test the data.
Deep Learning Model Works:

Advantages and disadvantages of deep learning:

(1) Advantage:
 Best in-class performance on problems.
 Reduces need for feature engineering.
 Eliminates unnecessary costs.
 Identifies defects easily that are difficult to detect.

(2) Disadvantage:
 Large amount of data required.
 Computationally expensive to train.
 No strong theoretical foundation.

Computer Vision:
 Computer vision is a process by which we can understand the images and videos
how they are stored and how we can manipulate and retrieve data from them.
Computer Vision is the base or mostly used for Artificial Intelligence. Computer-
Vision is playing a major role in self-driving cars, robotics as well as in photo
correction apps.

OpenCV:
 OpenCV is the huge open-source library for the computer vision, machine learning,
and image processing and now it plays a major role in real-time operation which is
very important in today’s systems. By using it, one can process images and videos
to identify objects, faces, or even handwriting of a human. When it integrated with
 various libraries, such as NumPy, python can process the OpenCV array structure
for analysis.

Application of Open CV:

 face recognition
 number of people – count (foot traffic in a mall, etc)
 Vehicle counting on highways along with their speeds.
 Anomaly (defect) detection in the manufacturing process (the odd
defective products)
 Video/image search and retrieval
 Robot and driver-less car navigation and control
 object recognition
 Medical image analysis
 TV Channels advertisement recognition

YoloV5:
 You Only Look Once (YOLO), this real-time object detection system. YOLOv5
processes images using a single neural network and then divides them into different
parts. This is done to increase accuracy, with each part getting its own anchor box
through an auto anchor process.
 The process is completely automated and it recomputes the anchor boxes if the
default ones are not accurate. With each part having its own box, the system
analyses and predicts the result.

Types of YOLOv5 Models :

 YOLOv5 has five models as listed below:

1. YoloV5n: This is the smallest and fastest model. It is also called the nano model and finds
applications in mobile devices owing to its size.
2. YoloV5s: This is also a comparatively small model. It is used to run results on
CPUs.
3. YoloV5m: As the “m” indicates, this is a medium-sized model.
4. YoloV5l: This is a large model.
5. YoloV5x: This is the top model of the variants. However, the size causes speed
compromises.
FireBase:
What is Firebase why it is used?
 0The Firebase Realtime Database lets you build rich, collaborative applications
by allowing secure access to the database directly from client-side code. Data
is persisted locally, and even while offline, realtime events continue to fire, giving the
end user a responsive experience.

What is Firebase and its types?

 The first Firebase product launched was the Realtime Database. It is an API
for application data synchronization across Android, web, and iOS devices.
Application developers can rely on the platform for creating collaborative real-
time applications.
Is Firebase a database?
 The Firebase Realtime Database is a cloud-hosted NoSQL database that lets you
store and sync data between your users in realtime.

What is the benefit of Firebase?

 One of the key advantages for Firebase's Realtime Database is that it works
offline by using local cache on the device to store any changes made.
Where Firebase can be used?
 Firebase Hosting works out-of-the-box with Firebase services, including Cloud
Functions, Authentication, Realtime Database, Cloud Firestore, and Cloud
 Messaging. You can build powerful microservices and web apps using these
complementary Firebase services.

Is Firebase a cloud?
 Yes! Firebase is Google's mobile development platform that empowers you to quickly
build and grow your app.

Does Firebase use SQL?

 Firebase uses NoSQL; MySQL uses SQL.

What type of data is Firebase?

 All Firebase Realtime Database data is stored as JSON objects. You can think of the
database as a cloud-hosted JSON tree. Unlike a SQL database, there are no tables
or records.

Why use Firebase instead of SQL?

 Compared to Firebase, MySQL is better for multi-row transactions. On the other
hand, Firebase is a satisfactory choice when it comes to managing huge data sets
because NoSQL horizontally scales data and it is much faster than MySQL. App
development platform from Google.

Is Firebase a framework?
 Firebase Hosting integrates with popular modern web frameworks including Angular
and Next.Js.