Generative AI

1. Variational Autoencoder.

Content: 

• Part-1
  • Basics of Autoencoders
  • Basics of Variational Autoencoders
  • Why Variational Autoencoder works like Generative Model but Traditional Autoencoder Not?
  • Step-by-Step discussion on Variational Autoencoder.
• Part-2.
  • Variational Autoencoder
  • Variational Inference
  • Computing - Cost function and other Mathematical formulations

Video Link: 

• Variational Autoencoder Part-1  (Direct Link: https://youtu.be/Mu7RoJHYqr4)

• Variational Autoencoder Part-2  (Direct Link: https://youtu.be/bdPgByjoSH4)

2. Generative Adversarial Network (GAN).

Content: 

• Part-1
  • Basics of GAN
  • Function and Technique behind:
    • Generator Model
    • Discriminator Model
    • GAN Architecture
  • GAN Loss Function
• Part-2.
  • Deep Convolutional GAN (DCGAN)
  • GAN key issues in Detail
    • Mode Collapse Problem
    • Training Instability
    • Overfitting Issues
  • Convolutional Up sampling 
  • Convolutional Down sampling
• Part-3 
  • Step-By-Step Process to write the code for DCGAN.
  • Detailed explanation behind each components of the code.

Video Link: 

• Generative Adversarial Network GAN Part-1  (Direct Link:https://youtu.be/TneKa3WHYO4)

• Generative Adversarial Network GAN Part-2  (Direct Link: https://youtu.be/rWh9ov9mR_I?si=jcuJSVacr4CXuVpy)

• Generative Adversarial Network GAN Part-3  (Direct Link: https://youtu.be/aBlvgN5w9sY?si=AjEP9jaira9vftNw)

3. Wasserstein GAN (WGAN).

Content: 

• Part-1
  • Basics of Wasserstein GAN.
  • Why we need Wasserstein Distance?
  • Difference between – (a) KL-Divergence, Vs (b) Jensen-Shannon Divergence Vs (c) Wasserstein Distance
• Part-2.
  • Wasserstein Distance.
  • Wasserstein Distance through -  (a) Kantrovich-Rubinstein Duality and (b) 1-Lipschitz Function
• Part-3 
  • Wasserstein GAN Architecture.
  • Wasserstein GAN KERAs implementation

Video Link: 

• Wasserstein GAN Part-1(KL-Divergence Vs Jensen-Shannon Divergence Vs Wasserstein Distance)  (Direct Link: https://youtu.be/4uEIMCa_BAo?si=6IP8qZogcQYokzjA)

• Wasserstein GAN Part-2 (Wasserstein Distance - Details)  (Direct Link: https://youtu.be/5hNgGSN8ScI?si=8QiUW0hksIYzgVfE)

• Wasserstein GAN Part-3 (Architecture and Implementation)  (Direct Link: https://youtu.be/m0oKu6u9X5o?si=Y1_yH4fmXDHj6fz6)

Self-Supervised Learning

1. Deep Clustering.

Content: 

• Basics of Self-Supervised Algorithm 
• Details of Deep Clustering
• Details of Cost Functions used in the Deep Clustering Algorithms 

Video Link: 

• Deep Clustering- Part-1 (A Self-Supervised Deep Learning Algorithm)  (Direct Link: https://youtu.be/j9KmEpaLers )

• Deep Clustering- Part-2 (A Self-Supervised Deep Learning Algorithm)  (Direct Link: https://youtu.be/Ca0r0ZbeHxM )

2. L2-Norm and Unit-Sphere for Contrastive/Self Supervised Learning.

Content: 

• Basics of L2-Norm 
• Basics of Unit-Sphere 
• Why we use both in Contrastive /Self-Supervised Learning. 

Video Link: 

• L2-Norm and Unit-Sphere for Contrastive/Self Supervised Learning  (Direct Link: https://youtu.be/X6TcKMA_rNY )

3. Self-Supervised Online Clustering (Unsupervised Learning of Visual Features).

Content: 

• Basics of Contrastive Learning 
• Paper Discussion: “Unsupervised Learning of Visual Features by Contrastive Cluster Assignments” 

Video Link: 

• Self-Supervised Online Clustering (Unsupervised Learning of Visual Features)  (Direct Link: https://youtu.be/3z8L4jGK2FE )

Trustable AI

1. Trustable AI -1.

Content: 

• Basics of Trustable AI 
• Uncertainty Estimation 
• Aleatoric Uncertainty 
• Epistemic Uncertainty 
• Model Reliability Model Calibration 

Video Link: 

• Trustable AI - Part-1  (Direct Link: https://youtu.be/lfMSBsW6GdE?si=aCHHpnFuEWnWcbKQ )

• Trustable AI - Part-2  (Direct Link: https://youtu.be/Un4T7SE2unU?si=1p6OpIcRWftNgnlh )