Scribd
Upload
21 views5 pages

Activity-1 DL

The document summarizes a student's report on an introduction to deep learning course. The course covered topics like ANN, CNN, RNN and their concepts. It also discussed deep learning frameworks like TensorFlow, PyTorch, Keras and applications of deep learning.

Uploaded by

Chitradeep Maji
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
21 views5 pages

Activity-1 DL

The document summarizes a student's report on an introduction to deep learning course. The course covered topics like ANN, CNN, RNN and their concepts. It also discussed deep learning frameworks like TensorFlow, PyTorch, Keras and applications of deep learning.

Uploaded by

Chitradeep Maji
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 5

DEPARTMENT OF MASTER OF

COMPUTER APPLICATION

ACTIVITY – 1
DEEP LEARNING

Name: Chitradeep Maji


USN No.: 22MCAR0006
Semester: 4th Semester
Branch: MCA (AI & ML)
Submitted to: Dr. Prerna Mahajan
Professor School of CS & IT
This is to certify that Chitradeep Maji satisfactorily completed the
course of Activity - 1 prescribed by the Jain (Deemed-to-be
University) for the Semester - 4 M.C.A(AI & ML) degree course in
the year 2022 -24.

USN No: 22MCAR0006

Signature of Student Head of the Department Signature of Faculty


REPORT ON
INTRODUCTION TO DEEP LEARNING:

Introduction:
The course "Introduction to Deep Learning" on Infosys
Springboard offers a comprehensive introduction about Deep learning and
covering topics such as Evolution and Introduction about deep learning, ANN,
CNN, RNN, Autoencoders and Frameworks of deep learning, etc., are the topics.
In this report, I will focus on the section of the course that covers briefly about
subtopics of ANN, CNN, RNN.

What I learned from the Course:

Evolution and Introduction:


Deep Learning, a subset of machine learning, has witnessed
remarkable growth and advancement in recent years. This report provides an
introduction to deep learning, its fundamental concepts, and its various
applications.
Deep Learning:
It refers to a class of machine learning techniques that are based
on artificial neural networks and are designed to model and solve complex
problems. Unlike traditional machine learning algorithms, deep learning
algorithms aim to automatically learn hierarchical representations of data directly
from raw inputs.

Artificial Neural Networks (ANN):


Artificial Neural Networks (ANNs) are the building blocks of deep
learning. They are composed of interconnected nodes or neurons arranged in
layers—input layer, hidden layers, and an output layer. ANNs are trained using a
process called backpropagation, where errors are propagated backward through the
network to adjust the weights and biases, optimizing the network's performance.

Convolutional Neural Networks (CNN):


Convolutional Neural Networks (CNNs) are a type of ANN
specifically designed for tasks involving structured grid-like data, such as images
and video. CNNs use convolutional layers to automatically learn and detect
patterns and features from visual data, making them highly effective in tasks like
image recognition, object detection, and image generation.

Recurrent Neural Networks (RNN):


Recurrent Neural Networks (RNNs) are neural networks that can
handle sequential data, making them suitable for tasks like natural language
processing, speech recognition, and time-series analysis. RNNs use recurrent
connections to process sequences, enabling them to maintain internal state and
capture dependencies over time.

Autoencoders:
Autoencoders are a type of neural network used for unsupervised
learning and dimensionality reduction. They consist of an encoder and a decoder,
where the encoder compresses data into a lower-dimensional representation
(encoding), and the decoder reconstructs the original data from the encoding.
Autoencoders are also used for tasks like anomaly detection and generative
modeling.

Deep Learning Frameworks and Products:


Several deep learning frameworks and products have emerged to
facilitate the development and deployment of deep learning models. Some popular
frameworks include:
TensorFlow: Developed by Google, TensorFlow is an open-source deep learning
framework known for its flexibility and scalability.

PyTorch: Developed by Facebook's AI Research lab (FAIR), PyTorch is known


for its dynamic computation graph and ease of use, making it a popular choice
among researchers.

Keras: Keras is a high-level neural networks API written in Python. It serves as an


interface for building and training deep learning models using frameworks like
TensorFlow and Theano.

Caffe: Caffe is a deep learning framework developed by the Berkeley Vision and
Learning Center, primarily used for computer vision tasks.

Conclusion:
I conclude that "Introduction to Deep Learning" course is helpful
for me to learn great things which is useful for the future purpose. In this I learned
topics like ANN, RNN, CNN and their sub-topics, Understanding the key concepts
and frameworks of deep learning is essential for anyone looking to harness its
potential and apply it to real-world problems and etc., tasks are learned and finally
the instructor gave an explanations and practical examples make the session better
way and understandable.

You might also like