🎉 🎉 🎉 Introducing Adaptive Training! 🎉 🎉 🎉

[alvaroe16]

This is great!! Thanks for sharing this!

Confirmed that the workout rankings are fixed… as Amber and Hubcyclist had said.

What changes is the Progression Category: “Achievable, Productive, Stretch, Breakthrough, Not Recommended” depending on your Progression Level.

Very cool… I could geek out on all of this data… can’t wait until I am accepted to the Beta…

[ccftri]

@YouburnEasy

The inclusion of outdoor rides in the ML will be such a game changer. So exciting for me even though most of my rides are indoors… can’t imagine the value this could have for people that do 80% plus of their rides outdoors

Honestly I don’t think the product even makes sense if it’s limited to only TR rides. I mean, I do a breakthrough effort on a local hill climb, or TT route, or ZRL race, but I have to come back and do that same effort on Carpathian Peak +2 or it doesn’t count? No way.

[mcneese.chad]

They know that, and that’s why Nate stated it as a high priority for them to finish and include. Sounds like they have a foundation and a bit more work to finish it.

This is all still beta stage, and not all features or functions are in place yet.

ETA: Mentions of unstructured, outside rides are around 1:20 and 1:57 in the cast.

[bbarrera]

And even once it leaves beta, this is just the beginning,

[Nate_Pearson]

Yes, this is the idea.

First step is to pull in the sleep data and see if it changes the likelihood of you finishing a workout. If that happens, we can adjust the workout/plan to have a better outcome.

[danredfern]

I am looking forward to trying the adaptive training when it comes out.
One question that I have is how will the AI system assess how well I performed on a workout?
Will it simply be binary; based on whether I completed vs failed a particular workout/interval?

Will it look at HR data for particular workout/interval and compare it to HR on previous workouts/power numbers? (Which is how I currently look for small improvements by comparing max/average HR for a workout I have done multiple times).

I have been using Trainer road for 6 years. Will the AI be able to retrospectively look at personal data from previous years?

[mcneese.chad]

Welcome to the forum, @danredfern .

I moved your post into the appropriate thread for discussion to keep it organized.

[roadbiketrevor]

I already started using my HRM with TrainerRoad as of yesterday evening’s workout, so I could start feeding data.

By the time this is all done I’ll have a chest HRM, Whoop strap, bike power meter, etc all piped into the TrainerRoad hive mind …

[Nate_Pearson]

@Battles

I’m hopeful this scale is fairly descriptive with regard to what level of effort each rating corresponds to. In other words, I think many of us aren’t a 100% clear on how physically challenging a workout should be to optimize adaptations vs being too challenging (even if we can eek it out) and potentially unproductive.

1 - Easy
2 - Moderate
3 - Hard
4 - Very Hard
5 - All Out

You don’t need to know what a workout should “feel” like. This is just how it felt for you. You might have an aerobic ride feel very hard because you’re thrashed, or you might have a vo2 ride feel moderate because you’re more fit than that level.

The idea is to not have anyone know what a ride should feel like relative to the workout. They just say on 1-5 how hard it was.

[denglish67]

That would be great. I have been manually noting my Whoop recovery and strain alongside each TR workout for the last 18 months, so would be fantastic if TR could simply suck it all up automatically and use it to adjust plan, particularly in relation to fatigue/recovery.

[jarsson]

I really like your style:)

[DeSti1569]

I really really wish there was an option to add an endurance chunk at the end of workouts and not just a cooldown. Right now I have to finish a cooldown and then load up an endurance workout which usually has a small ramp. Kind of defeats the purpose a bit.

[enki42]

@roadbiketrevor

By the time this is all done I’ll have a chest HRM, Whoop strap, bike power meter, etc all piped into the TrainerRoad hive mind

Next you’ll need accurate sensors (not whoop going by dcrainmaker, so will need a Garmin watch which gets the same basic info)

[roadbiketrevor]

Garmin’s sleep tracking is WHACK. I have a garmin watch and it’s good for HR and GPS but not sleep. It’s a known issue. They’d be better off not even having sleep as a feature.

[Twinans]

This may have been asked but will the ML adjust for time of day for the workout? For instance sometimes I do an “easy” morning workout just to wake up and get moving, like dans or petit, but because its in the morning and I typically train in the afternoon my R.P.E in the morning is almost always “moderate” or in super rare occasions “Hard”. Sometimes I have even turned the intensity down on lazy mountain in the morning but I sort of view these rides as separate from my training. Would the best way to make sure these don’t negatively effect future rides would be to just not accept the plan adaptions after these rides? Or will the ML learn to turn down my intensity in the morning but not in the afternoon or evening?

[Nate_Pearson]

@paulgrav

Agree but my point was that stating a single value for RPE for an entire workout doesn’t provide the full picture. An RPE of 7 could mean that it was somewhat hard the whole time or it could mean that the workout start off at a 6 and finished at an eight.

When I write my workout notes, I tend write stuff like “RPE: 6 but the last two intervals were 7”. There’s no software in existence that is capturing RPE over time, unlike for HR.

If TR is going to use a combination of RPE in addition to HR, great!

I don’t think we’ll need that much fine grain control. I could be wrong though.

But I want to stress this so hard…it’s not just “one” thing anymore. It’s hundreds of things and we might never understand the true relationship between everything.

And as we get more sophisticated and have access to more data we hope to make everything more accurate.

[enki42]

The newer sleep tracking in the fenix 6? Garmin Shows Off New On-Device Sleep Tracking Widgets | DC Rainmaker

[Nate_Pearson]

@jmdcovas

@Nate_Pearson Off-topic but relevant: you should do an IPO so we can get some TR stonks.

TR to the moon

That would be sweet. We could do the first round that’s usually for bankers but make it just for TR users. And the more workouts you have in TR the more you could buy.

No plans for investment or IPO at this time though.

I’ve got a pretty big timeline goal in my head and I don’t want the external pressure to cut corners and get quarterly results.

[Nate_Pearson]

Yes, we understand the difference between a pause during a 5 min rest interval to go to the bathroom and a pause in the middle of a 10 minute over-under set to make it easier.

This is one of the many reasons we used ML and not just do interval averages.

We had to classify thousands of rides that had different pause amounts to order for it to learn.

Even a bathroom pause in a Baxter should be fine.

[Nate_Pearson]

@jchappers

I think (Nate?) said the next batch would be another ‘by invitation only’ then they will start down the list of sign ups. I took from that it’ll be at least a few days.

Yah, we have some early people in and we’re getting feedback on bugs/confusion already. We’ll want to fix those things then expand.

How these programs usually work are they are kind of exponential. They start out slow then as our confidence goes up they increase faster and faster.