SlideShare a Scribd company logo
1 of 40
Introduction to Generative Models
Unleashing the Power of Artificial Creativity
Submitted by : Abdul Latif Faqeeri
Submitted to : Ms. Rama Rani
Univ Roll : 22073010
What are Generative Models?
● Generative models create new data based on
existing patterns
● Popular examples include Generative Adversarial
Networks (GANs) and Variational Autoencoders
(VAEs)
● They enable machines to generate art, music, and
text
● Generative models have applications in data
augmentation, simulation, and creativity
Photo by Pexels
Autoencoders
● An unsupervised deep learning
algorithm Unlabeled
data
● Are Artificial Neural Networks
● Useful for dimensionality
reduction and feature learning
● X bar is x’s reconstruction
● Z is some latent representation
or code and S is a non linearity
such as the sigmoid.
Photo by Pexels
Autoencoders
Photo by Pexels
Stacked Autoencoder
Photo by Pexels
Implementing a stacked Autoencoder Using Keras
Photo by Pexels
Visualizing the Reconstructions
Photo by Pexels
One way to ensure that an autoencoder is properly trained is to compare
the inputs and the outputs: the differences should not be too significant.
Unsupervised Pretraining using Stacked Autoencoder
Photo by Pexels
Transfer Learning
Training One Autoencoder at a Time
Photo by Pexels
Convolutional Autoencoders
Photo by Pexels
● If dealing with images
● Autoencoders so far will not work ? ( unless the images are very small )
Denoising Autoencoders
Photo by Pexels
Denoising Autoencoders
Photo by Pexels
Variational Autoencoders
Photo by Pexels
● An important category of autoencoders was introduced in 2013 by
Diederik Kingma and Max Welling and quickly became one of the
most popular variants: variational autoencoders (VAEs)
● VAEs are quite different from all the autoencoders we have
discussed so far, in these particular ways:
1. They are probabilistic autoencoders, meaning that their
outputs are partly determined by chance, even after training (as
opposed to denoising autoencoders, which use randomness only
during training)
2. Most importantly, they are generative autoencoders, meaning that
they can generate new instances that look like they were sampled
from the training set.
Variational Autoencoders
Photo by Pexels
Variational Autoencoders
Photo by Pexels
Application in Natural Language Processing
● Generative models are used in language modeling
and text generation
● They can generate realistic text, dialogue, and even
poetry
● They have applications in chatbots, language
translation, and content creation
● Generative models can inspire creative writing and
art
Photo by Pexels
Challenges in Generative Model Training
● Training generative models can be computationally
intensive
● Mode collapse is a common problem, where the model
generates limited variety
● Evaluating the quality of generated content is subjective
and challenging
● Overfitting and loss of diversity are other challenges to
address
Photo by Pexels
Applications in Medical Imaging
● Generative models are used for medical image
generation and synthesis
● They can create synthetic images for training and
data augmentation
● Generative models aid in disease diagnosis and
treatment planning
● They enable medical research and simulations
Photo by Pexels
Ethical Considerations
● Generative models raise concerns about misuse and
manipulation
● Deep fakes and fake news propagation are examples of
potential harm
● Regulations and guidelines need to be developed to
mitigate risks
● User education and awareness are crucial in addressing
ethical challenges
Photo by Pexels
Future Trends in Generative Models
● Advancements in generative models continue to
expand its possibilities
● Integration with reinforcement learning can enhance
creativity
● Research focuses on improving stability and diversity
of generated content
● Applications in robotics, virtual reality, and design are
emerging
Photo by Pexels
Open-source Frameworks for Generative Models
● Popular open-source frameworks include TensorFlow,
PyTorch, and Keras
● These frameworks provide pre-trained models and
resources
● Community support facilitates knowledge sharing and
collaboration
● Developers can experiment and contribute to the field
Photo by Pexels
Generative Adversarial Networks (GANs)
Unlocking the Power of AI Creativity
Introduction to GANs
● GANs are a class of machine learning models.
● They consist of two neural networks: a generator and a
discriminator.
● The generator creates synthetic data, while the
discriminator tries to distinguish between real and fake
data.
● GANs have revolutionized the field of AI by enabling
advanced image and content generation.
Photo by Pexels
Photo by Pexels
How GANs Work
● The generator network takes random
noise as input and generates data.
● The discriminator network receives
both real and fake data and learns to
distinguish between them.
● The generator and discriminator are
trained simultaneously through a
process of competition and
cooperation.
● This iterative process leads to the
generator generating increasingly
realistic data.
Photo by Pexels
Let’s go ahead and build a simple GAN for Fashion MNIST.
Photo by Pexels
The Power of GANs
● GANs consist of a generator and a discriminator network
● The generator learns to create realistic data, while the
discriminator learns to distinguish real from fake
● GANs have revolutionized image synthesis and style
transfer
● They are used in deepfake technology and image super-
resolution
Photo by Pexels
Applications of GANs
● GANs have been used in various
creative fields, such as art, music,
and fashion.
● They can generate realistic
images, textures, and even
human-like faces.
● GANs have also been used for
data augmentation, anomaly
detection, and domain adaptation.
● The applications of GANs
continue to expand across
industries.
Photo by Pexels
Training Challenges
● GAN training can be challenging
due to mode collapse and
instability.
● Mode collapse occurs when the
generator produces limited
variations of data.
● Instability refers to the difficulty in
achieving equilibrium between the
generator and discriminator.
● Researchers are actively working
on techniques to stabilize GAN
training. Photo by Pexels
GAN Variants
● Several variants of GANs have been
developed to address specific
challenges.
● DCGAN (Deep Convolutional GAN)
uses convolutional networks for
image generation.
● CycleGAN can translate images
from one domain to another without
paired training data.
● StyleGAN allows control over the
generated images style and
characteristics.
Photo by Pexels
Ethical Considerations
● GANs raise ethical concerns
regarding the generation of deep
fakes and manipulated content.
● They can be misused for phishing,
impersonation, and spreading
misinformation.
● Regulations and ethical guidelines
are being developed to mitigate
these risks.
● Responsible and ethical use of
GANs is crucial for preserving
trust in AI technology.
Photo by Pexels
Future Developments
● Research in GANs is advancing
rapidly, pushing the boundaries of
AI creativity.
● Improved training algorithms and
architectures are being
developed.
● GANs are expected to have
broader applications in virtual
reality, advertising, and
healthcare.
● The future holds tremendous
potential for the continued Photo by Pexels
Diffusion Models
● ideas behind diffusion models have been around for
many years
● first formalized in their modern form in a 2015 paper by
Jascha Sohl-Dickstein et al. from Stanford University
and UC Berkeley
● The authors applied tools from thermodynamics to
model a diffusion process.
● What is diffusion process ?
Photo by Pexels
Photo by Pexels
Diffusion Models
● The core idea is to train a model to learn the reverse
process: start from the completely mixed state, and
gradually “unmix” the milk from the tea.
● they obtained promising results in image generation
● since GANs produced more convincing images back then,
diffusion models did not get as much attention.
● in 2020, Jonathan Ho et al., also from UC Berkeley,
managed to build a diffusion model capable of generating
highly realistic images, which they called a denoising
diffusion probabilistic model (DDPM)
Photo by Pexels
Diffusion Models
● A few months later, a 2021 paper by OpenAI researchers
Alex Nichol and Prafulla Dhariwal analyzed the DDPM
architecture and proposed several improvements that
allowed DDPMs to finally beat GANs.
Photo by Pexels
Diffusion Models
Photo by Pexels
Diffusion Models
Photo by Pexels
References
Photo by Pexels
Géron, A. (2019). Hands-On Machine Learning with Scikit-Learn, Keras,
and TensorFlow. O'Reilly Media.
Photo by Pexels
ਤੁਹਾਡਾ ਧੰਨਵਾਦ

More Related Content

Similar to Introduction to Generative Models.pptx

leewayhertz.com-Generative AI in manufacturing.pdf
leewayhertz.com-Generative AI in manufacturing.pdfleewayhertz.com-Generative AI in manufacturing.pdf
leewayhertz.com-Generative AI in manufacturing.pdfKristiLBurns
 
Gen AI_Object Automation_TechnologyWorkshop
Gen AI_Object Automation_TechnologyWorkshopGen AI_Object Automation_TechnologyWorkshop
Gen AI_Object Automation_TechnologyWorkshopObject Automation
 
Deep learning for real life applications
Deep learning for real life applicationsDeep learning for real life applications
Deep learning for real life applicationsAnas Arram, Ph.D
 
leewayhertz.com-Getting started with generative AI A beginners guide.pdf
leewayhertz.com-Getting started with generative AI A beginners guide.pdfleewayhertz.com-Getting started with generative AI A beginners guide.pdf
leewayhertz.com-Getting started with generative AI A beginners guide.pdfrobertsamuel23
 
Model evaluation in the land of deep learning
Model evaluation in the land of deep learningModel evaluation in the land of deep learning
Model evaluation in the land of deep learningPramit Choudhary
 
Zilliz - Overview of Generative models in ML
Zilliz - Overview of Generative models in MLZilliz - Overview of Generative models in ML
Zilliz - Overview of Generative models in MLZilliz
 
7-200404101602.pdf
7-200404101602.pdf7-200404101602.pdf
7-200404101602.pdfssuser07e9f2
 
Landscape of AI/ML in 2023
Landscape of AI/ML in 2023Landscape of AI/ML in 2023
Landscape of AI/ML in 2023HyunJoon Jung
 
Report of Previous Project by Yifan Guo
Report of Previous Project by Yifan GuoReport of Previous Project by Yifan Guo
Report of Previous Project by Yifan GuoYifan Guo
 
Deep Learning and the state of AI / 2016
Deep Learning and the state of AI / 2016Deep Learning and the state of AI / 2016
Deep Learning and the state of AI / 2016Grigory Sapunov
 
An Introduction To Generative Adversarial Networks
An Introduction To Generative Adversarial NetworksAn Introduction To Generative Adversarial Networks
An Introduction To Generative Adversarial NetworksBluebash LLC
 
Deep Generative Modelling
Deep Generative ModellingDeep Generative Modelling
Deep Generative ModellingPetko Nikolov
 
Crafting Recommenders: the Shallow and the Deep of it!
Crafting Recommenders: the Shallow and the Deep of it! Crafting Recommenders: the Shallow and the Deep of it!
Crafting Recommenders: the Shallow and the Deep of it! Sudeep Das, Ph.D.
 
100-Concepts-of-AI with Anupama Kate .pptx
100-Concepts-of-AI with Anupama Kate .pptx100-Concepts-of-AI with Anupama Kate .pptx
100-Concepts-of-AI with Anupama Kate .pptxAnupama Kate
 
Generative AI or GenAI technology based PPT
Generative AI or GenAI technology based PPTGenerative AI or GenAI technology based PPT
Generative AI or GenAI technology based PPTbhaskargani46
 
H2O with Erin LeDell at Portland R User Group
H2O with Erin LeDell at Portland R User GroupH2O with Erin LeDell at Portland R User Group
H2O with Erin LeDell at Portland R User GroupSri Ambati
 

Similar to Introduction to Generative Models.pptx (20)

Journey of Generative AI
Journey of Generative AIJourney of Generative AI
Journey of Generative AI
 
leewayhertz.com-Generative AI in manufacturing.pdf
leewayhertz.com-Generative AI in manufacturing.pdfleewayhertz.com-Generative AI in manufacturing.pdf
leewayhertz.com-Generative AI in manufacturing.pdf
 
Gen AI_Object Automation_TechnologyWorkshop
Gen AI_Object Automation_TechnologyWorkshopGen AI_Object Automation_TechnologyWorkshop
Gen AI_Object Automation_TechnologyWorkshop
 
Deep learning for real life applications
Deep learning for real life applicationsDeep learning for real life applications
Deep learning for real life applications
 
leewayhertz.com-Getting started with generative AI A beginners guide.pdf
leewayhertz.com-Getting started with generative AI A beginners guide.pdfleewayhertz.com-Getting started with generative AI A beginners guide.pdf
leewayhertz.com-Getting started with generative AI A beginners guide.pdf
 
Model evaluation in the land of deep learning
Model evaluation in the land of deep learningModel evaluation in the land of deep learning
Model evaluation in the land of deep learning
 
Zilliz - Overview of Generative models in ML
Zilliz - Overview of Generative models in MLZilliz - Overview of Generative models in ML
Zilliz - Overview of Generative models in ML
 
Generative models
Generative modelsGenerative models
Generative models
 
7-200404101602.pdf
7-200404101602.pdf7-200404101602.pdf
7-200404101602.pdf
 
QAI brochure
QAI brochureQAI brochure
QAI brochure
 
Landscape of AI/ML in 2023
Landscape of AI/ML in 2023Landscape of AI/ML in 2023
Landscape of AI/ML in 2023
 
Report of Previous Project by Yifan Guo
Report of Previous Project by Yifan GuoReport of Previous Project by Yifan Guo
Report of Previous Project by Yifan Guo
 
What is Generative AI and How does it works?
What is Generative AI and How does it works?What is Generative AI and How does it works?
What is Generative AI and How does it works?
 
Deep Learning and the state of AI / 2016
Deep Learning and the state of AI / 2016Deep Learning and the state of AI / 2016
Deep Learning and the state of AI / 2016
 
An Introduction To Generative Adversarial Networks
An Introduction To Generative Adversarial NetworksAn Introduction To Generative Adversarial Networks
An Introduction To Generative Adversarial Networks
 
Deep Generative Modelling
Deep Generative ModellingDeep Generative Modelling
Deep Generative Modelling
 
Crafting Recommenders: the Shallow and the Deep of it!
Crafting Recommenders: the Shallow and the Deep of it! Crafting Recommenders: the Shallow and the Deep of it!
Crafting Recommenders: the Shallow and the Deep of it!
 
100-Concepts-of-AI with Anupama Kate .pptx
100-Concepts-of-AI with Anupama Kate .pptx100-Concepts-of-AI with Anupama Kate .pptx
100-Concepts-of-AI with Anupama Kate .pptx
 
Generative AI or GenAI technology based PPT
Generative AI or GenAI technology based PPTGenerative AI or GenAI technology based PPT
Generative AI or GenAI technology based PPT
 
H2O with Erin LeDell at Portland R User Group
H2O with Erin LeDell at Portland R User GroupH2O with Erin LeDell at Portland R User Group
H2O with Erin LeDell at Portland R User Group
 

Recently uploaded

The basics of sentences session 3pptx.pptx
The basics of sentences session 3pptx.pptxThe basics of sentences session 3pptx.pptx
The basics of sentences session 3pptx.pptxheathfieldcps1
 
On National Teacher Day, meet the 2024-25 Kenan Fellows
On National Teacher Day, meet the 2024-25 Kenan FellowsOn National Teacher Day, meet the 2024-25 Kenan Fellows
On National Teacher Day, meet the 2024-25 Kenan FellowsMebane Rash
 
Application orientated numerical on hev.ppt
Application orientated numerical on hev.pptApplication orientated numerical on hev.ppt
Application orientated numerical on hev.pptRamjanShidvankar
 
Basic Civil Engineering first year Notes- Chapter 4 Building.pptx
Basic Civil Engineering first year Notes- Chapter 4 Building.pptxBasic Civil Engineering first year Notes- Chapter 4 Building.pptx
Basic Civil Engineering first year Notes- Chapter 4 Building.pptxDenish Jangid
 
Graduate Outcomes Presentation Slides - English
Graduate Outcomes Presentation Slides - EnglishGraduate Outcomes Presentation Slides - English
Graduate Outcomes Presentation Slides - Englishneillewis46
 
Beyond_Borders_Understanding_Anime_and_Manga_Fandom_A_Comprehensive_Audience_...
Beyond_Borders_Understanding_Anime_and_Manga_Fandom_A_Comprehensive_Audience_...Beyond_Borders_Understanding_Anime_and_Manga_Fandom_A_Comprehensive_Audience_...
Beyond_Borders_Understanding_Anime_and_Manga_Fandom_A_Comprehensive_Audience_...Pooja Bhuva
 
Unit 3 Emotional Intelligence and Spiritual Intelligence.pdf
Unit 3 Emotional Intelligence and Spiritual Intelligence.pdfUnit 3 Emotional Intelligence and Spiritual Intelligence.pdf
Unit 3 Emotional Intelligence and Spiritual Intelligence.pdfDr Vijay Vishwakarma
 
How to Manage Global Discount in Odoo 17 POS
How to Manage Global Discount in Odoo 17 POSHow to Manage Global Discount in Odoo 17 POS
How to Manage Global Discount in Odoo 17 POSCeline George
 
REMIFENTANIL: An Ultra short acting opioid.pptx
REMIFENTANIL: An Ultra short acting opioid.pptxREMIFENTANIL: An Ultra short acting opioid.pptx
REMIFENTANIL: An Ultra short acting opioid.pptxDr. Ravikiran H M Gowda
 
Jamworks pilot and AI at Jisc (20/03/2024)
Jamworks pilot and AI at Jisc (20/03/2024)Jamworks pilot and AI at Jisc (20/03/2024)
Jamworks pilot and AI at Jisc (20/03/2024)Jisc
 
Spellings Wk 3 English CAPS CARES Please Practise
Spellings Wk 3 English CAPS CARES Please PractiseSpellings Wk 3 English CAPS CARES Please Practise
Spellings Wk 3 English CAPS CARES Please PractiseAnaAcapella
 
UGC NET Paper 1 Mathematical Reasoning & Aptitude.pdf
UGC NET Paper 1 Mathematical Reasoning & Aptitude.pdfUGC NET Paper 1 Mathematical Reasoning & Aptitude.pdf
UGC NET Paper 1 Mathematical Reasoning & Aptitude.pdfNirmal Dwivedi
 
Wellbeing inclusion and digital dystopias.pptx
Wellbeing inclusion and digital dystopias.pptxWellbeing inclusion and digital dystopias.pptx
Wellbeing inclusion and digital dystopias.pptxJisc
 
Salient Features of India constitution especially power and functions
Salient Features of India constitution especially power and functionsSalient Features of India constitution especially power and functions
Salient Features of India constitution especially power and functionsKarakKing
 
Unit-V; Pricing (Pharma Marketing Management).pptx
Unit-V; Pricing (Pharma Marketing Management).pptxUnit-V; Pricing (Pharma Marketing Management).pptx
Unit-V; Pricing (Pharma Marketing Management).pptxVishalSingh1417
 
Understanding Accommodations and Modifications
Understanding  Accommodations and ModificationsUnderstanding  Accommodations and Modifications
Understanding Accommodations and ModificationsMJDuyan
 
Towards a code of practice for AI in AT.pptx
Towards a code of practice for AI in AT.pptxTowards a code of practice for AI in AT.pptx
Towards a code of practice for AI in AT.pptxJisc
 
80 ĐỀ THI THỬ TUYỂN SINH TIẾNG ANH VÀO 10 SỞ GD – ĐT THÀNH PHỐ HỒ CHÍ MINH NĂ...
80 ĐỀ THI THỬ TUYỂN SINH TIẾNG ANH VÀO 10 SỞ GD – ĐT THÀNH PHỐ HỒ CHÍ MINH NĂ...80 ĐỀ THI THỬ TUYỂN SINH TIẾNG ANH VÀO 10 SỞ GD – ĐT THÀNH PHỐ HỒ CHÍ MINH NĂ...
80 ĐỀ THI THỬ TUYỂN SINH TIẾNG ANH VÀO 10 SỞ GD – ĐT THÀNH PHỐ HỒ CHÍ MINH NĂ...Nguyen Thanh Tu Collection
 
Making communications land - Are they received and understood as intended? we...
Making communications land - Are they received and understood as intended? we...Making communications land - Are they received and understood as intended? we...
Making communications land - Are they received and understood as intended? we...Association for Project Management
 

Recently uploaded (20)

The basics of sentences session 3pptx.pptx
The basics of sentences session 3pptx.pptxThe basics of sentences session 3pptx.pptx
The basics of sentences session 3pptx.pptx
 
On National Teacher Day, meet the 2024-25 Kenan Fellows
On National Teacher Day, meet the 2024-25 Kenan FellowsOn National Teacher Day, meet the 2024-25 Kenan Fellows
On National Teacher Day, meet the 2024-25 Kenan Fellows
 
Application orientated numerical on hev.ppt
Application orientated numerical on hev.pptApplication orientated numerical on hev.ppt
Application orientated numerical on hev.ppt
 
Basic Civil Engineering first year Notes- Chapter 4 Building.pptx
Basic Civil Engineering first year Notes- Chapter 4 Building.pptxBasic Civil Engineering first year Notes- Chapter 4 Building.pptx
Basic Civil Engineering first year Notes- Chapter 4 Building.pptx
 
Graduate Outcomes Presentation Slides - English
Graduate Outcomes Presentation Slides - EnglishGraduate Outcomes Presentation Slides - English
Graduate Outcomes Presentation Slides - English
 
Beyond_Borders_Understanding_Anime_and_Manga_Fandom_A_Comprehensive_Audience_...
Beyond_Borders_Understanding_Anime_and_Manga_Fandom_A_Comprehensive_Audience_...Beyond_Borders_Understanding_Anime_and_Manga_Fandom_A_Comprehensive_Audience_...
Beyond_Borders_Understanding_Anime_and_Manga_Fandom_A_Comprehensive_Audience_...
 
Unit 3 Emotional Intelligence and Spiritual Intelligence.pdf
Unit 3 Emotional Intelligence and Spiritual Intelligence.pdfUnit 3 Emotional Intelligence and Spiritual Intelligence.pdf
Unit 3 Emotional Intelligence and Spiritual Intelligence.pdf
 
How to Manage Global Discount in Odoo 17 POS
How to Manage Global Discount in Odoo 17 POSHow to Manage Global Discount in Odoo 17 POS
How to Manage Global Discount in Odoo 17 POS
 
REMIFENTANIL: An Ultra short acting opioid.pptx
REMIFENTANIL: An Ultra short acting opioid.pptxREMIFENTANIL: An Ultra short acting opioid.pptx
REMIFENTANIL: An Ultra short acting opioid.pptx
 
Jamworks pilot and AI at Jisc (20/03/2024)
Jamworks pilot and AI at Jisc (20/03/2024)Jamworks pilot and AI at Jisc (20/03/2024)
Jamworks pilot and AI at Jisc (20/03/2024)
 
Spellings Wk 3 English CAPS CARES Please Practise
Spellings Wk 3 English CAPS CARES Please PractiseSpellings Wk 3 English CAPS CARES Please Practise
Spellings Wk 3 English CAPS CARES Please Practise
 
UGC NET Paper 1 Mathematical Reasoning & Aptitude.pdf
UGC NET Paper 1 Mathematical Reasoning & Aptitude.pdfUGC NET Paper 1 Mathematical Reasoning & Aptitude.pdf
UGC NET Paper 1 Mathematical Reasoning & Aptitude.pdf
 
Wellbeing inclusion and digital dystopias.pptx
Wellbeing inclusion and digital dystopias.pptxWellbeing inclusion and digital dystopias.pptx
Wellbeing inclusion and digital dystopias.pptx
 
Salient Features of India constitution especially power and functions
Salient Features of India constitution especially power and functionsSalient Features of India constitution especially power and functions
Salient Features of India constitution especially power and functions
 
Mehran University Newsletter Vol-X, Issue-I, 2024
Mehran University Newsletter Vol-X, Issue-I, 2024Mehran University Newsletter Vol-X, Issue-I, 2024
Mehran University Newsletter Vol-X, Issue-I, 2024
 
Unit-V; Pricing (Pharma Marketing Management).pptx
Unit-V; Pricing (Pharma Marketing Management).pptxUnit-V; Pricing (Pharma Marketing Management).pptx
Unit-V; Pricing (Pharma Marketing Management).pptx
 
Understanding Accommodations and Modifications
Understanding  Accommodations and ModificationsUnderstanding  Accommodations and Modifications
Understanding Accommodations and Modifications
 
Towards a code of practice for AI in AT.pptx
Towards a code of practice for AI in AT.pptxTowards a code of practice for AI in AT.pptx
Towards a code of practice for AI in AT.pptx
 
80 ĐỀ THI THỬ TUYỂN SINH TIẾNG ANH VÀO 10 SỞ GD – ĐT THÀNH PHỐ HỒ CHÍ MINH NĂ...
80 ĐỀ THI THỬ TUYỂN SINH TIẾNG ANH VÀO 10 SỞ GD – ĐT THÀNH PHỐ HỒ CHÍ MINH NĂ...80 ĐỀ THI THỬ TUYỂN SINH TIẾNG ANH VÀO 10 SỞ GD – ĐT THÀNH PHỐ HỒ CHÍ MINH NĂ...
80 ĐỀ THI THỬ TUYỂN SINH TIẾNG ANH VÀO 10 SỞ GD – ĐT THÀNH PHỐ HỒ CHÍ MINH NĂ...
 
Making communications land - Are they received and understood as intended? we...
Making communications land - Are they received and understood as intended? we...Making communications land - Are they received and understood as intended? we...
Making communications land - Are they received and understood as intended? we...
 

Introduction to Generative Models.pptx

  • 1. Introduction to Generative Models Unleashing the Power of Artificial Creativity Submitted by : Abdul Latif Faqeeri Submitted to : Ms. Rama Rani Univ Roll : 22073010
  • 2. What are Generative Models? ● Generative models create new data based on existing patterns ● Popular examples include Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs) ● They enable machines to generate art, music, and text ● Generative models have applications in data augmentation, simulation, and creativity Photo by Pexels
  • 3. Autoencoders ● An unsupervised deep learning algorithm Unlabeled data ● Are Artificial Neural Networks ● Useful for dimensionality reduction and feature learning ● X bar is x’s reconstruction ● Z is some latent representation or code and S is a non linearity such as the sigmoid. Photo by Pexels
  • 6. Implementing a stacked Autoencoder Using Keras Photo by Pexels
  • 7. Visualizing the Reconstructions Photo by Pexels One way to ensure that an autoencoder is properly trained is to compare the inputs and the outputs: the differences should not be too significant.
  • 8. Unsupervised Pretraining using Stacked Autoencoder Photo by Pexels Transfer Learning
  • 9. Training One Autoencoder at a Time Photo by Pexels
  • 10. Convolutional Autoencoders Photo by Pexels ● If dealing with images ● Autoencoders so far will not work ? ( unless the images are very small )
  • 13. Variational Autoencoders Photo by Pexels ● An important category of autoencoders was introduced in 2013 by Diederik Kingma and Max Welling and quickly became one of the most popular variants: variational autoencoders (VAEs) ● VAEs are quite different from all the autoencoders we have discussed so far, in these particular ways: 1. They are probabilistic autoencoders, meaning that their outputs are partly determined by chance, even after training (as opposed to denoising autoencoders, which use randomness only during training) 2. Most importantly, they are generative autoencoders, meaning that they can generate new instances that look like they were sampled from the training set.
  • 16. Application in Natural Language Processing ● Generative models are used in language modeling and text generation ● They can generate realistic text, dialogue, and even poetry ● They have applications in chatbots, language translation, and content creation ● Generative models can inspire creative writing and art Photo by Pexels
  • 17. Challenges in Generative Model Training ● Training generative models can be computationally intensive ● Mode collapse is a common problem, where the model generates limited variety ● Evaluating the quality of generated content is subjective and challenging ● Overfitting and loss of diversity are other challenges to address Photo by Pexels
  • 18. Applications in Medical Imaging ● Generative models are used for medical image generation and synthesis ● They can create synthetic images for training and data augmentation ● Generative models aid in disease diagnosis and treatment planning ● They enable medical research and simulations Photo by Pexels
  • 19. Ethical Considerations ● Generative models raise concerns about misuse and manipulation ● Deep fakes and fake news propagation are examples of potential harm ● Regulations and guidelines need to be developed to mitigate risks ● User education and awareness are crucial in addressing ethical challenges Photo by Pexels
  • 20. Future Trends in Generative Models ● Advancements in generative models continue to expand its possibilities ● Integration with reinforcement learning can enhance creativity ● Research focuses on improving stability and diversity of generated content ● Applications in robotics, virtual reality, and design are emerging Photo by Pexels
  • 21. Open-source Frameworks for Generative Models ● Popular open-source frameworks include TensorFlow, PyTorch, and Keras ● These frameworks provide pre-trained models and resources ● Community support facilitates knowledge sharing and collaboration ● Developers can experiment and contribute to the field Photo by Pexels
  • 22. Generative Adversarial Networks (GANs) Unlocking the Power of AI Creativity
  • 23. Introduction to GANs ● GANs are a class of machine learning models. ● They consist of two neural networks: a generator and a discriminator. ● The generator creates synthetic data, while the discriminator tries to distinguish between real and fake data. ● GANs have revolutionized the field of AI by enabling advanced image and content generation. Photo by Pexels
  • 25. How GANs Work ● The generator network takes random noise as input and generates data. ● The discriminator network receives both real and fake data and learns to distinguish between them. ● The generator and discriminator are trained simultaneously through a process of competition and cooperation. ● This iterative process leads to the generator generating increasingly realistic data. Photo by Pexels
  • 26. Let’s go ahead and build a simple GAN for Fashion MNIST. Photo by Pexels
  • 27. The Power of GANs ● GANs consist of a generator and a discriminator network ● The generator learns to create realistic data, while the discriminator learns to distinguish real from fake ● GANs have revolutionized image synthesis and style transfer ● They are used in deepfake technology and image super- resolution Photo by Pexels
  • 28. Applications of GANs ● GANs have been used in various creative fields, such as art, music, and fashion. ● They can generate realistic images, textures, and even human-like faces. ● GANs have also been used for data augmentation, anomaly detection, and domain adaptation. ● The applications of GANs continue to expand across industries. Photo by Pexels
  • 29. Training Challenges ● GAN training can be challenging due to mode collapse and instability. ● Mode collapse occurs when the generator produces limited variations of data. ● Instability refers to the difficulty in achieving equilibrium between the generator and discriminator. ● Researchers are actively working on techniques to stabilize GAN training. Photo by Pexels
  • 30. GAN Variants ● Several variants of GANs have been developed to address specific challenges. ● DCGAN (Deep Convolutional GAN) uses convolutional networks for image generation. ● CycleGAN can translate images from one domain to another without paired training data. ● StyleGAN allows control over the generated images style and characteristics. Photo by Pexels
  • 31. Ethical Considerations ● GANs raise ethical concerns regarding the generation of deep fakes and manipulated content. ● They can be misused for phishing, impersonation, and spreading misinformation. ● Regulations and ethical guidelines are being developed to mitigate these risks. ● Responsible and ethical use of GANs is crucial for preserving trust in AI technology. Photo by Pexels
  • 32. Future Developments ● Research in GANs is advancing rapidly, pushing the boundaries of AI creativity. ● Improved training algorithms and architectures are being developed. ● GANs are expected to have broader applications in virtual reality, advertising, and healthcare. ● The future holds tremendous potential for the continued Photo by Pexels
  • 33. Diffusion Models ● ideas behind diffusion models have been around for many years ● first formalized in their modern form in a 2015 paper by Jascha Sohl-Dickstein et al. from Stanford University and UC Berkeley ● The authors applied tools from thermodynamics to model a diffusion process. ● What is diffusion process ? Photo by Pexels
  • 35. Diffusion Models ● The core idea is to train a model to learn the reverse process: start from the completely mixed state, and gradually “unmix” the milk from the tea. ● they obtained promising results in image generation ● since GANs produced more convincing images back then, diffusion models did not get as much attention. ● in 2020, Jonathan Ho et al., also from UC Berkeley, managed to build a diffusion model capable of generating highly realistic images, which they called a denoising diffusion probabilistic model (DDPM) Photo by Pexels
  • 36. Diffusion Models ● A few months later, a 2021 paper by OpenAI researchers Alex Nichol and Prafulla Dhariwal analyzed the DDPM architecture and proposed several improvements that allowed DDPMs to finally beat GANs. Photo by Pexels
  • 39. References Photo by Pexels Géron, A. (2019). Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow. O'Reilly Media.