šŸŽ‰ šŸŽ‰ šŸŽ‰ Introducing Adaptive Training! šŸŽ‰ šŸŽ‰ šŸŽ‰

Hi Nate
Wow A personal reply :+1::+1::+1:

I know you are thinking this but you are about to change training forever …

I use the type of software in the UK for pricing retail insurance and we look for predictive life time value to price both new business and renewals

I was a pro triathlete (once apon a time many moons ago) and now am a sociable cyclist looking for a balance from being CFO of a three thousand employee business

Anyway . Would love to have an offline with you on some of our key learnings as I really think you are creating a game changer

If i don’t here back the very very best of luck and continue to be an excellent CEO :+1::+1:

6 Likes

You nailed it! We trained the model to take into account trainer lag.

This is one of the many reasons why we couldn’t just do average power in intervals. That was our first approach and it failed.

9 Likes

Thanks for the response Nate

I am not in the beta yet, but I have been tracking all of these measurements via Oura Ring and HRVTraining for a while. Is there a place that I can record these in TR or provide it through some other means so that the data science team can start to collect this data? I know how important collecting the source data is, and I would like to help in any way I can.

You can see my post above. Basically we should allow the next wave in very soon.

If I put in a hard timeline people will complain no matter what. We’re sort of in a damned if we do, damned if we don’t situation.

18 Likes

I think its awesome that you come on the forum and post feedback to all of our questions. Chapeau sir.

@Nate_Pearson

22 Likes

Gender is a feature on the ML model.

ML will detect if there’s relevant difference between male/female.

And the progression system already takes this into account. If you’re better/worse at anaerobic efforts we’ll find that out and adapt.

So it’s more fine grain than just gender; it’s individual to you.

10 Likes

If you’re marking the workouts with a low RPE and they are supposed to be a high RPE you will progress faster.

You can also use Workout Alternatives and try a ā€œstretchā€ workout. That will also progress you more quickly.

4 Likes

No, not right now. We’d need to record differences in different power meters and have someone type them in or something like that.

1 Like

Correct. Or you can use Workout Alternatives and select a 90 minute workout.

Workout Alternatives gives you a bit more fine grain control. It shows you 90 minute workouts at the same level and workout profile.

We think Workout Alternatives is the better option in this scenario.

11 Likes

Next people will probably get in this week depending on the PR status of the one above.

New features will come to EVERYONE in weeks, not months.

Of course, I could get burned by this statement if we have a very bad bug.

25 Likes

Deleted workouts would be considered like time off or a skipped workout. So the next week would most likely get a bit easier.

5 Likes

If it’s a ramp test it won’t have any impact.

If you ā€œstruggle/failā€ in a workout due to a device issue there’s a survey option to say you had a device issue. That makes our ML ignore it.

Yesterday I had Kaiser+2 planned but subbed it for Kaiser-1, how would AT deal with that? I.e. still doing a workout in the same energy zone as that planned but either easier, as in this case, or harder?

Based on what you actually did.

So in the Z5 to Z2 it would be an ā€œeasyā€ workout.

I would suggest using Train Now for this scenario. Just ride how you feel and choose what workout looks interesting to you.

2 Likes

Very exciting. I just got my new Kickr Core, can’t wait to get added to the Beta.

2 Likes

But how much time is not equal to how much volume you should do.

IE I technically could ride 5 hours per day, every day, but I shouldn’t!

2 Likes

It will not. We ignore warm up/cool down.

6 Likes

Thanks! I think I might do my own post about how athletes want to be communicated to.

Half the people seem to like me being open with roadmap and priorities.

The other half see it as ā€œteasingā€, being dishonest, and need hard timelines.

34 Likes

Agree completely. Given the huge hype of the podcast, the rollout is a decided meh. More clarity on timelines would be very helpful. For such a data driven company TR really ought to be able to provide at least minimal reporting on numbers in the beta queue & daily movement. With slightly more effort it should be possible for TR to show people where they are in the queue, assuming they signed up to the beta with the same email address they normally use. If we are really talking months before the AT features are rolled out on a large scale to the willing beta testers, they should have just kept quite for awhile.

1 Like