inflearn logo

From MLE to an Introduction to AE·VAE | TTD Diffusion Lecture Available for Free

In fact, artificial neural networks were outputting distributions! We’re making the introductory section on MLE, AE, and VAE from TTD: To The Diffusion available for free. Understand neural network outputs and loss functions through maximum likelihood estimation, then connect PCA and autoencoders to latent-variable-based image generation and why VAEs are necessary. A total of 5 lessons, approximately 2 hours and 26 minutes.

1 learners are taking this course

Level Basic

Course period Unlimited

Deep Learning(DL)
Deep Learning(DL)
Deep Learning(DL)
Deep Learning(DL)
Thumbnail

What you will gain after the course

  • Understanding Neural Network Outputs from a Probability Distribution Perspective

  • Understanding Deep Learning’s Learning Principles from the Perspective of Maximum Likelihood Estimation (MLE)

  • Understanding PCA·AE compression and reconstruction, latent-variable-based image generation, and the need for VAEs

Recommended for
these people

Who is this course right for?

  • Those who want to gain a deeper understanding of neural network outputs and loss functions

  • Those who want to understand the difference between AE and VAE, and why latent variables and probabilistic models are needed for image generation.

Need to know before starting?

  • Fundamental Concepts of Artificial Neural Networks and Deep Learning Training

  • It would be good to have a basic understanding of probability and probability distributions. You don't need to know VAE or diffusion models in advance.

Hello
This is hyukppen

Hello. I’m Hyeokpenheim, a deep learning instructor with a Ph.D. from the KAIST School of Electrical Engineering. After working as a principal researcher at Samsung Electronics and as an adjunct lecturer at the School of Medicine at Sungkyunkwan University, I currently run Hyeokpenheim Academy. I am the author of *Easy! Deep Learning*, an introductory book on deep learning, and have 11 years of teaching experience, having taught approximately 3,000 students in total. I specialize in deep learning theory and PyTorch practice, covering CNNs, transformers, LLMs and vision models, diffusion, and more.

Rather than simply memorizing model architectures or equations, I explain why each idea emerged and how it works. Starting with intuitive analogies, I clarify the meaning of the equations and connect them to code, with the goal of helping learners explain what they have learned in their own words and build a foundation for reading papers in depth.

On the YouTube channel “Hyukpenheim,” we offer lectures ranging from basic mathematics and Python to advanced deep learning topics, as well as providing on-site lectures and training for schools, companies, and organizations.

More

Curriculum

All

5 lectures ∙ (2hr 26min)

Published: 
Last updated: 

Reviews

Not enough reviews.
Please write a valuable review that helps everyone!

hyukppen's other courses

Check out other courses by the instructor!

Similar courses

Explore other courses in the same field!

Free