SEED Research & Announcements Blogs Publications Open Source Careers Contact Us Research & Announcements Blogs Publications Open Source Careers Contact Us

GDC & GTC 2018

SEED

Next week at Game Developers Conference 2018, we will have 4 talks from developers at SEED sharing some of the latest results and work that our group have done within real-time rendering, deep learning AI, and procedural content creation.

The slides for the presentations will also be posted here on our page shortly after the conference.

Here is an overview of the talks we are doing at GDC 2018:

DirectX: Evolving Microsoft's Graphics Platform
(presented by Microsoft)

Speakers: Matt Sandy (Microsoft), Johan Andersson & Colin Barré-Brisebois
Location: Room 2009, West Hall
Date: Wednesday, March 21
Time: 3:30pm - 4:30pm

For over 20 years, DirectX has been the platform used by game developers to create the fastest, most visually impressive games on the planet. Come and learn our plans to deliver the next generation of graphics innovation.

Shiny Pixels and Beyond: Rendering Research at SEED
(presented by NVIDIA)


Speakers: Johan Andersson & Colin Barré-Brisebois
Location: Room 3022, West Hall
Date: Wednesday, March 21
Time: 5:00pm - 6:00pm

In this talk, we will present results from the latest research from SEED, a cross-disciplinary team working on cutting-edge, future graphics technologies and creative experiences at Electronic Arts.

We will explain in detail the techniques from our research, so that attendees can understand how these results were achieved. We hope to inspire developers and provide a glimpse of the future with novel rendering techniques that could power the creative experiences of tomorrow.

Deep Learning: Beyond the Hype


Speaker: Magnus Nordin
Location: Room 2016, West Hall
Date: Thursday, March 22
Time: 11:30am - 12:30pm

No-one will have missed the rapid rise of deep learning over the past years. Neural nets have enabled significant breakthroughs in everything from computer vision, voice generation, voice recognition, translation, to self-driving cars. Neural nets will also be a powerful enabler for future game development. This presentation will give an overview of the potential of neural nets in game development, as well as provide an in depth look at how you can use neural nets combined with reinforcement learning for new types of game AI. From now on, neural nets will be a powerful new tool in the software engineering toolbox.

Takeaway

The audience will gain an understanding of the wide variety of applications of neural nets in game development, and will see a preview of the most powerful new tool in software engineering in decades.

Creativity of Rules and Patterns: Designing Procedural Systems


Speaker: Anastasia Opara
Location: GDC Show Floor, Booth #341
Date & Time: Thursday, March 22 @ 12:30PM-1:00PM and Friday, March 23 @ 11:00AM-11:30AM

Human mechanisms of representing the surrounding world in a form of ‘language’ is an outstanding ability that enables us to store the information as internal compact abstractions. Proceduralism is also a form of language, where we view the world through rules, dependencies and patterns. And though rules are often perceived as something rigid, their engineering is a fluid and creative task, where analyzing our own thought framework often fuels the design process.


 

The week after GDC, Nvidia is arranging the GPU Technology Conference (GTC) where we will present more in-depth on our deep reinforcement learning work:

Deep Reinforcement Learning for 3D Multiplayer Games


Speaker: Magnus Nordin
Location: Room 230B
Date: Monday, Mar 26
Time: 10:00 AM - 10:50 AM

Over the last couple of years, neural nets have enabled significant breakthroughs in computer vision, voice generation and recognition, translation, and self-driving cars. Neural nets will also be a powerful enabler for future game development. We'll give an overview of the potential of neural nets in game development, as well as provide an in-depth look at how we can use neural nets combined with reinforcement learning for new types of game AI.

 


 

Other talks from friends across Electronic Arts during GDC 2018:

 

Related News

Incorporating ML Research Into Audio Production: ExFlowSions Case Study

SEED
Jun 25, 2024
Mónica Villanueva and Jorge García present the challenges and lessons learned from turning a machine learning generative model from a research project into a game production tool.

Beyond White Noise for Real-Time Rendering

SEED
May 14, 2024
SEED’s Alan Wolfe discusses the use of different types of noise for random number generation, focusing on the application of blue noise in rendering images for gaming.

Evaluating Gesture Generation in a Large-Scale Open Challenge

SEED
May 9, 2024
This paper, published in Transactions on Graphics, reports on the second GENEA Challenge, a project to benchmark data-driven automatic co-speech gesture generation.