Scribd
Upload
6 views7 pages

Introduction To Deep Learning

The document outlines a course on Deep Learning (EL 4149) taught by Dr. Divya Rishi Shrivastava, covering its fundamentals, key characteristics, and common architectures such as CNNs, RNNs, and GANs. It highlights the importance of large datasets and computational power in training deep learning models, as well as various applications including computer vision, natural language processing, and healthcare. The content is intended for educational purposes and does not claim copyright over the material presented.

Uploaded by

sakshamparadox
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
6 views7 pages

Introduction To Deep Learning

The document outlines a course on Deep Learning (EL 4149) taught by Dr. Divya Rishi Shrivastava, covering its fundamentals, key characteristics, and common architectures such as CNNs, RNNs, and GANs. It highlights the importance of large datasets and computational power in training deep learning models, as well as various applications including computer vision, natural language processing, and healthcare. The content is intended for educational purposes and does not claim copyright over the material presented.

Uploaded by

sakshamparadox
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/ 7

B.Tech.

Electrical &
Computer Department of Electrical
Engineering Engineering
7 th Semester

Deep Learning Course Instructor


(EL 4149) Dr Divya Rishi Shrivastava
Assistant Professor (Selection Grade)
Department of Electrical Engineering
Lecture 1

• Introduction
• Course Hand-out briefing

Disclaimer: The presenter do not claim any copyright of the content shown here in any way. These content are referred from internet and used for education purpose only.
Deep learning is a subset of machine learning, which itself is a subset of artificial
intelligence (AI).
• It involves the use of artificial neural networks (ANNs) with many layers—hence
the term "deep."
• These neural networks are designed to mimic the human brain's way of
processing data and creating patterns for use in decision making.

Key Characteristics of Deep Learning:

Artificial Neural • Deep learning models are built using ANNs, which are structured in layers: an input layer,
Networks (ANNs): multiple hidden layers, and an output layer.

• The "deep" in deep learning refers to the number of hidden layers in the neural network.
Layers: Traditional machine learning models typically use one or two hidden layers, while deep learning
models use many more, sometimes dozens or even hundreds.

• Unlike traditional machine learning, which often requires manual feature extraction, deep
Feature Learning:
learning automatically discovers the representations needed for classification or prediction.

Large Data • Deep learning models generally require large amounts of data to perform effectively, as they
Requirements: need to learn a vast number of parameters.

High Computational • Training deep learning models often requires significant computational resources, such as GPUs
Power: (Graphics Processing Units), TPUs (Tensor Processing Units), or specialized hardware.
3
Generative
Convolutional Recurrent Neural
Adversarial
Neural Networks Networks Transformers:
Networks
(CNNs): (RNNs):
(GANs):

Common
Architectures Suitable for
in Deep Primarily Used for
sequential State-of-the-
Learning: used for generating
data, such art models
image new data
as time for natural
recognition that is
series or language
and similar to a
natural processing
processing given
language tasks.
tasks. dataset.
processing.

4
Applications of Deep Learning:

Computer Vision:
• Object detection, facial recognition, image classification.

Natural Language Processing:


• Language translation, sentiment analysis, text generation.

Speech Recognition:
• Voice assistants, transcription services.

Healthcare:
• Disease detection, personalized treatment plans.

Autonomous Vehicles:
• Self-driving cars, advanced driver-assistance systems.

5
6
Course Hand-out briefing

You might also like