Scribd
Upload
12 views13 pages

Unit5 PPT

The document provides an introduction to deep learning, highlighting the differences between machine learning and deep learning. It outlines four major architectures of deep networks: Unsupervised Pretrained Networks, Convolutional Neural Networks, Recurrent Neural Networks, and Recursive Neural Networks, along with their use cases. The content is sourced from various references and is intended for educational purposes.

Uploaded by

23bme020
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
12 views13 pages

Unit5 PPT

The document provides an introduction to deep learning, highlighting the differences between machine learning and deep learning. It outlines four major architectures of deep networks: Unsupervised Pretrained Networks, Convolutional Neural Networks, Recurrent Neural Networks, and Recursive Neural Networks, along with their use cases. The content is sourced from various references and is intended for educational purposes.

Uploaded by

23bme020
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/ 13

Introduction

to
Deep Learning
Introduction
⮚ AI, ML and DL

These slides are not original and have been


Source: [1] prepared from various sources for teaching
purpose
2
Introduction
⮚ Machine Learning vs Deep Learning

These slides are not original and have been


Source: [2] prepared from various sources for teaching
purpose
3
Introduction
⮚ Machine Learning vs Deep Learning

Source of the Image:


https://editor.analyticsvidhya.com/uploads/51518iris%20img1.png
These slides are not original and have been
prepared from various sources for teaching 4
purpose
Major Architectures of Deep Networks
⮚ Four Major Architectures:
⮚ Unsupervised Pretrained Networks (UPNs)
⮚ Convolutional Neural Networks (CNNs)
⮚ Recurrent Neural Networks
⮚ Recursive Neural Networks

These slides are not original and have been


prepared from various sources for teaching 5
purpose
Major Architectures of Deep Networks
⮚ Four Major Architectures:
⮚ Unsupervised Pretrained Networks (UPNs)
⮚ Autoencoders
⮚ Deep Belief Networks (DBNs)
⮚ Generative Adversarial Networks (GANs)

⮚ Use Cases:
⮚ Feature Extraction
⮚ Synthesizing

These slides are not original and have been


Source: [3] prepared from various sources for teaching
purpose
6
Major Architectures of Deep Networks
⮚ Four Major Architectures:
⮚ Convolutional Neural Networks (CNNs)
⮚ Lenet-5
⮚ AlexNet
⮚ VGGNet
⮚ GoogleNet (Inception)
⮚ ResNet
⮚ ResNext
⮚ DenseNet
⮚ RCNN (Region Based CNN)
⮚ YOLO (You Only Look Once)
⮚ SqueezeNet
⮚ SegNet

These slides are not original and have been


prepared from various sources for teaching 7
purpose
Major Architectures of Deep Networks
⮚ Four Major Architectures:
⮚ Convolutional Neural Networks (CNNs)
⮚ Use Cases:
⮚ Computer Vision
⮚ Natural Language Processing

These slides are not original and have been


prepared from various sources for teaching 8
purpose
Major Architectures of Deep Networks
⮚ Four Major Architectures:
⮚ Recurrent Neural Networks
⮚ Hopfield Network
⮚ Long Short-Term Memory (LSTM)
⮚ Gated Recurrent Unit (GRU)
⮚ Use Cases:
⮚ Sentiment Classification
⮚ Image Captioning
⮚ Language Translation
⮚ Video Captioning

These slides are not original and have been


prepared from various sources for teaching 9
purpose
Major Architectures of Deep Networks
⮚ Four Major Architectures:
⮚ Recursive Neural Networks
⮚ Recursive Autoencoder
⮚ Recursive Neural Tensor Network
⮚ Use Cases:
⮚ Image scene decomposition
⮚ NLP
⮚ Audio-to-text transcription

These slides are not original and have been


prepared from various sources for teaching 10
purpose
References
1. https://towardsdatascience.com/the-10-deep-learning-
methods-ai-practitioners-need-to-apply-885259f402c1

2. https://semiengineering.com/deep-learning-spreads/

3. https://www.safaribooksonline.com/library/view/deep-
learning/9781491924570/ch04.html
“We invented fire, repeatedly messed up, and
then invented the fire extinguisher, fire exit,
fire alarm and fire department.”
Disclaimer
⮚ Content of this presentation is not original and it
has been prepared from various sources for
teaching purpose.

You might also like