Dr. Sean Humbert is back on GEAR:30 to provide an update on our ski testing at Blister Labs; discuss the potential of artificial intelligence and machine learning for product reviewing and ski recommendation engines; and more.
TOPICS & TIMES:
- Skier, Biker, Mechanical Engineer (4:00)
- Update on Blister Labs Ski Testing (5:35)
- Artificial Intelligence & Ski Testing (9:48)
- Ski Recommendation Engines (16:20)
- Other Labs Initiatives + AI Engine Compatibility (21:42)
- Crashes & Close Calls (26:00)
- What We’re Celebrating (29:51)
RELATED LINKS:
CHECK OUT OUR OTHER PODCASTS:
- CRAFTED
- Blister Podcast
- Bikes & Big Ideas
- Off the Couch
- Happy Hour (for Blister Members)
Is this the same guy behind the https://soothski.com/ ?
No, that’s Alexis at Université de Sherbrooke in Sherbrooke Quebec. He’s the man ;)
I gotta say, using AI/ML to classify skis isn’t very inspiring. Maybe it’ll lead to new features being discovered to along with stiffness, taper, weight, etc, but classifying a known quantity (they’re already ‘classed’ by the manufacturers & reviewers, you’re not dealing with mystery skis) seems pretty mundane. It’s like a solution looking for a problem. Maybe it’ll help manufacturers optimize their design features for specific traits though, or have other exciting applications. I guess we’ll see!
Just to be clear, we’re not merely talking about “classifying” skis here – surely you know that we could care less whether someone calls a ski a ‘frontside’ ski or ‘all-mountain’ ski … it’s all about communicating the specific details of how a product works and where it does and doesn’t shine.
The potential here is to be getting into much finer and more accurate points of performance characteristics of skis, and that (as you rightly suspect) could have significant benefits for manufacturers (e.g., speeding up the prototyping process – not an insignificant thing). Plus, we’ll continue to explore how it could refine and improve the ski testing process and our ski recommendation process.