Ideas
Explore the world's #1 largest database of ideas and innovations, with over 400,000 inspiring examples.
Insights
Uncover major shifts and emerging opportunities with our exclusive PRO research.
Trend Reports
Discover why 750 brands rely on our AI-powered Trend Reports to get better, faster insights.
Newsletter
Join over 200,000 subscribers who rely on our weekly newsletter to keep up with need-to-know trends and insights.
Books
Join 20,000,000+ people getting better and faster with our New York Times Bestselling methods, best innovation books & keynote videos.
Dashboard
Get special access to premium content, topic tracking and customizable tools through our AI-powered Dashboard.
AI
Learn how the Trend Hunter harnesses the power of artificial intelligence.
Assessment
Enhance your innovation potential with a deeper understanding of your unique innovation archetype and how your organization benchmarks.
Overview
Accelerate innovation and ignite disruptive thinking with our award-winning programs and research.
Keynotes, Workshops & Webinars
Empower your team with the insights and frameworks they need to innovate better and faster.
Custom Research
Get fast, customized trend reports, presentations and deep dives 20x faster than traditional research.
Plans
Get started today with a free consultation, our self-serve tools, or a dedicated program.
Jeremy Gutsche
Ignite your event or virtual event with our CEO, a NY Times Bestselling Author and one of the top innovation keynote speakers.
Our Team of Speakers & Virtual Presenters
Inspire your group with our most popular speakers on innovation, trends, change and futurism.
Contact
Get in touch to learn more, ask a question or submit a tip.
About Us
Learn more about Trend Hunter and how we accelerate innovation.
FAQ
Get answers to common questions about Trend Hunter.
Community
Stay on the cutting-edge with the help of the Trend Hunter community.
Team
Meet the team trusted by hundreds of leading businesses worldwide.
Jobs
Find opportunities to accelerate your career with the #1 Trend Firm.
Internships
Grow your professional skillset in an award-winning workplace.
News
Catch up on noteworthy Trend Hunter news and media mentions.
Join
Build a portfolio and put your trend-spotting abilities to the test.
Advertising
Supercharge your marketing by partnering with Trend Hunter.
Portfolio
Visit your public portfolio and browse your past articles.
Add a Trend
Write up an article and showcase your trend-spotting skills.
My Trends
Edit your articles and see how they stack up on the leaderboards.
Settings
Edit your profile, connect your social media accounts, and more.
Add a trend, customize your dashboard, or track topics.
Future Festival
World Summit
Join the world's top innovators at our 3-Day Toronto event.
eLearning (NEW)
Prepare for the year's ahead with 100+ lessons, tactics, tools and frameworks with our full learning database.
Virtual Events (NEW!)
Stream our World Summit content from the comfort of your home.
Free Webinars
During COVID-19, learn to innovate through chaos, navigate the new normal and maintain work culture from home.
Innovation Events
Explore our 2020 tour dates and find the best city to inspire your team.
Custom Events
Host a custom innovation conference in your city that will inform and inspire.
Custom Training
Bring the Future Festival experience directly to your team with custom training packages.
Search our database of over 390,000 cutting edge ideas.

Neural Network Character Controls

Daniel Holden Created Neural Networks for Character Control

— May 3, 2017 — Tech
Daniel Holden, a researcher from the University of Edinburgh, has recently designed a new system of character control that promises to not only make character movements in video games look more realistic but also to ensure that games run more smoothly in general. Announced in a paper released by the university entitled 'Phase-Functioned Neural Networks for Character Control,' the system uses neural networks in order to give characters a wide range of motion while drawing from a relatively small database.

In games up until now, characters moved by combining series of pre-designed animations stored locally on the game's device or the disc itself. This system is both data heavy and constrained, since the characters can only move in set patterns. Holden's neural network relies on motion data collected from actual footage of a model in motion, trimming from that to invent any independent movement.
2.4
Score
Popularity
Activity
Freshness