ASSIGNMENT ON
Deep Learning
Course Code: CSE-3217 Course Title: Technical Writing and Presentation Lab
Submitted By:
Submitted By:
Name: Abir Hasan
Anup Majumder
Roll: 05
Assistant Professor
Department of Computer Science &
Department of Computer
Engineering
Science & Engineering
Session: 2019-2020
Jahangirnagar university
Year: 3rd year 2nd semester
Submission Date: 17 August 2023
Department of Computer Science & Engineering
Sheikh Hasina University
Netrokona, Bangladesh
1|Page
Introduction:
Deep learning is a subset of machine learning, It is mainly a neural network
with three or more layers. Deep learning mainly focus on works for Artificial
intelligence(AI) applications and services that improve automation, physical
tasks without human intervention. Deep learning technology lies behind
everyday products and services in our life. It is the important element of data
science, including statistics.
Where human brains have millions of interconnected neurons that work together
to learn information, Deep learning features also neural networks constructed
from multiple layers of software nodes that work together.
This assignment aims to provide a comprehensive overview of deep learning,
covering its fundamental concepts, applications across different domains, and its
potential future prospects.
Fundamental Concepts of Deep Learning:
To know about Deep learning, we first need to know its position. Let’s describe
it with a figure.
Artificial Intelligence
Machine learning
Neural Network
Deep learning
2|Page
Artificial Intelligence (AI) refers to the simulation of human intelligence
processes by machines, especially computer systems.
Machine Learning (ML) is a subset of artificial intelligence (AI) that focuses
on the development of algorithms and models that allow computers to learn
from data and make predictions or decisions without being explicitly
programmed.
A Neural Network is a computational model inspired by the structure and
functioning of the human brain.
Deep learning is based on artificial neural networks (ANNs). They are networks
of simple nodes that are interconnected and can learn to recognize patterns of
input. Artificial neural networks are similar to the brain in that they are
composed of many interconnected processing nodes. Each node is connected to
various other nodes. They have a weight that determines the strength of the
connection.
Deep Learning Architectures:
There are some types of deep learning model
Convolutional Neural Networks(CNN)
Recurrent Neural Networks(RNN)
Long Short-Term Memory(LSTM)
Convolutional Neural Networks (CNN)
Convolutional neural networks (or just convolutional networks) are commonly
used to analyze visual content.
They are similar to regular neural networks, but they have an extra layer of
processing that helps them to better identify patterns in images.
Recurrent Neural Networks (RNN)
A recurrent neural network (RNN) is a type of artificial neural network where
connections between nodes form a directed graph along a sequence. This allows
it to exhibit temporal dynamic behavior.
Long Short-Term Memory (LSTM)
3|Page
Long short-term memory networks are a type of recurrent neural network that
can learn and remember long-term dependencies. They are often used in
applications such as natural language processing and time series prediction.
Why Deep Learning?
Deep learning play a crucial role in determining the features and can handle the
large number of processes for the data that might be structured . Although, deep
learning can overkill some tasks that might involve complex problems because
they need access to huge amounts of data so that they can function effectively.
For example, there is a popular deep learning tool that recognizes images
namely Imagenet that has access to 14 million images in its dataset-driven.
Representation Learning: Deep learning algorithms excel at learning
hierarchical representations of data. These representations capture
features and patterns at different levels of abstraction, allowing the
algorithm to understand and distinguish intricate relationships within the
data.
Handling Large and Complex Data: Deep learning models are well-
suited for handling large volumes of data, such as images, audio, text, and
sensor data.
Feature Engineering Automation: Traditional machine learning often
requires manual feature engineering, which can be time-consuming and
domain-specific. Deep learning, on the other hand, automates this process
by learning relevant features directly from the data, reducing the need for
extensive hand-crafted feature design.
Scalability: Deep learning algorithms can take advantage of modern
parallel computing and GPU acceleration, allowing them to process large
datasets and perform complex computations efficiently.
Applications of Deep Learning:
Most common deep learning applications are computer vision, natural language
processing, healthcare, finance, agriculture, and cybersecurity. We will discuss
how deep learning is being used in these fields and the benefits it provides.
Computer Vision: Most artificial intelligence applications have been
developed on the shoulders of computer vision, and deep learning has
4|Page
made significant advancements in computer vision, including object
detection, image classification, and image segmentation.
Natural Language Processing: Natural language processing (NLP) is
the field of study that focuses on the interaction between human language
and computers. Deep learning has transformed the field of NLP, enabling
computers to interpret and respond to human language. One of the key
applications of deep learning in NLP is machine translation.
Healthcare: Deep learning improves medical imaging in healthcare,
including CT and MRI scans, and it allows specialists to develop more
accurate and personalized treatment plans.
Finance: Deep learning has shown significant potential to revolutionize
the financial industry, with a wide range of applications that can help
improve decision-making, risk management, fraud detection, and
customer experience.
Cybersecurity: Cybersecurity also uses deep learning to improve threat
detection and response. Cybersecurity threats are becoming increasingly
sophisticated, and traditional rule-based approaches are insufficient to
detect and prevent attacks.
Conclusion:
Deep learning's proficiency in handling large amounts of structured data has led
to significant advancements in areas like medical diagnosis, autonomous
vehicles, and financial analysis. However, it's important to note that the
effectiveness of deep learning models often hinges on the availability of
substantial and diverse datasets. While these models excel at tasks with
abundant data, they may struggle with more complex problems that require
nuanced understanding or reasoning beyond what's represented in the data.
Furthermore, the development and training of deep learning models can be
resource-intensive and computationally demanding. This can lead to challenges
in terms of time, energy consumption, and the need for specialized hardware.
5|Page
