DataHour: Diffusion Model Fundamentals and Various Applications

DataHour: Diffusion Model Fundamentals and Various Applications

07 Sep 202315:09pm - 07 Sep 202316:09pm

DataHour: Diffusion Model Fundamentals and Various Applications

About the Event

Discover the transformative world of image generation that has captivated creatives and permeated daily life. Generative Models, the driving force behind this evolution, have broken free from academia to reshape our reality. Dive into the essence of generative modelling, encompassing VAEs, GANs, and Flow Models, which have a long history.

Enter Diffusion Models, a game-changer that democratized generative modelling. These models deliver astonishing outcomes with simplicity in learning and training. Yet, their intricate mathematical foundation can seem daunting, creating a barrier to entry. In this talk, we will also look at some non-image use cases of diffusion models and what it takes to apply diffusion models on arbitrary data structures, which is often the case in industrial setups. We will also look at some peculiar use cases of the diffusion model, which are beyond "just generation".

  1. Best articles get published on Analytics Vidhya’s Blog Space
  2. Best articles get published on Analytics Vidhya’s Blog Space
  3. Best articles get published on Analytics Vidhya’s Blog Space
  4. Best articles get published on Analytics Vidhya’s Blog Space
  5. Best articles get published on Analytics Vidhya’s Blog Space

Who is this DataHour for?

  1. Best articles get published on Analytics Vidhya’s Blog Space
  2. Best articles get published on Analytics Vidhya’s Blog Space
  3. Best articles get published on Analytics Vidhya’s Blog Space

About the Speaker

Ayan Das

Ayan Das

Senior DL Research Scientist at MediaTek

Ayan Das is a Senior DL research scientist at MediaTek Research UK and a final year PhD student at the University of Surrey UK. Ayan holds an academic as well as industrial role and works on both theoretical and applied research. His broad domain of interest is the Generative Modelling of images and other non-image data modalities like discrete and continuous sequences. Currently, he is developing fundamental algorithmic improvement for faster sampling in diffusion models, a problem that bothers the community in terms of practical deployment.

Participate in discussion

Registration Details

7994

Registered

Become a Speaker

Share your vision, inspire change, and leave a mark on the industry. We're calling for innovators and thought leaders to speak at our event

  • Professional Exposure
  • Networking Opportunities
  • Thought Leadership
  • Knowledge Exchange
  • Leading-Edge Insights
  • Community Contribution