🎉 🎉 🎉 Introducing Adaptive Training! 🎉 🎉 🎉

[jzhowie]

Same

[Hampstenfan]

@mcneese.chad, does this work when the original plan was set in Plan Builder? It seems when I tweak what’s there it tells me I can no longer make changes, and end up having to build a new plan with a modified start date to get me to where I am today – but not sure how I can modify going forward without having to do that again for a second mod.

[mcneese.chad]

No, my mods are not Plan Builder friendly. If you want to follow my alterations, it’s easiest to just add them via the old methods, not PB.

Anytime I tried using Plan Builder, it created more of a mess.

[mrpedro]

To powermatch means that you use the power data of your power meter to control the smart trainer resistance and get comparable data this way.

But if you don’t wan’t or can’t switch over the outside power meter for inside rides, that is not possible. I have the same thing as I use a hometrainer for inside and don’t want to switch power pedals all the time.

This could be a solution: https://www.fitfiletools.com
It allows you to take a fit file and adjust the power data with a fixed %, before uploading to TR.

[SeeEl]

And some power meters will allow you to adjust the slope so you can bring it more into line with the trainer. First job really is to get the outside power meter on the trainer and do a varied workout and record both separately and compare the power outputs of both. If you can adjust the slope of your power meter and bring it to within a reasonable difference of your trainer you can continue using separate bikes (and power meters) indoors and out. @dcrainmaker has a power file comparison tool on his website and quite possibly articles or videos on this whole topic. Hopefully someone else will chime in with more detail on the specifics.

[Nate_Pearson]

@wbendus

@Nate_Pearson Might SMO2 and/or THb data from a Moxy sensor provide some useful insight to how prepared the muscles are to work…?

Maybe. This is hard because not many people have this device. With new measurement devices, you get into a chicken/egg situation.

I think there’s lower hanging fruit at first to feed into the model.

[Nate_Pearson]

@Snowflake69

@Brad_Hanson

Does adaptive training differentiate between a completed workout that just kills you versus a completed workout that was easy?

Exactly what I was wondering after completing Palisade yesterday where over unders became a VO2 session though I gutted it out to near death!

Yes, this is what the survey response is for. You give an RPE response of 1-5.

This is really important for us to know. Imagine the changes that could happen if Palisade was a “5 - All out” vs a “1 - Easy”.

[Nate_Pearson]

@Landon_Tong

One thing I’m curious about…using a dumb trainer with speed / cadence sensors and bluetooth connection to my iPad, there is a bit of lag between the power im putting out and the power TR sees, especially on short intervals like vo2 or short sprints. Sometimes it will show that I didnt hit my target for the interval because by the time it was over, TR had just caught up.

So here’s the question…Will adaptive training see this as me not hitting my workout targets and scale my training back incorrectly?

Super excited about the development and I love everything TrainerRoad is doing. Thanks yall!

Yes, this is built into the workout classifier and why we couldn’t just use average interval power.

We looked at a bunch of workouts with short power spikes and had a human classify them to the best of their ability. This taught the ML to recognize ones that is clear someone is hitting the prescribed goal even if they are off by a few seconds (usually due to device lag).

[Nate_Pearson]

@Flashpoint51

FWIW, I just went through the Baird/Bashful combo and found them pretty much the same - the extra 2% in the intervals is amply compensated for by the longer recovery valleys.

That is very insightful because they are the exact same level .

[Nate_Pearson]

@D-9

Has there been any talk of TR sharing a list of workouts with their rating numbers? This would help a bunch of people make manual tweaks to our schedules while we await AT access. It might keep Chad Mcneese from having to constantly provide this info on random workouts people ask him about.

We’re hoping to get levels out to everyone on Monday, March 15th 2021. This is subject to bugs and could be pushed out.

[Kaj_Johnson]

[enki42]

@Nate_Pearson

Maybe. This is hard because not many people have this device. With new measurement devices, you get into a chicken/egg situation.

I agree that very few people have muscle oxygen sensors (humon devices that are out there would also broadcast over ant+ so just as easy to read) but the data is just a simple stream of numbers like HR and FIT files already have a standardized place to store the data. So shouldn’t be that hard to just reuse the code for recording HR data to record to a different location. (this is in comparison to HRV that doesn’t just update once a second so is more complicated to capture) Just collect the data first. Add the ability to pair over Ant+ and if its paired save it. No UI changes to show the data. (at least at first) Just collect it so it can be looked at later

Plus if you’re the first platform to use the data you might get Moxy to push some people to use your platform. The current software that does this isn’t as nice to use.

[enki42]

@Nate_Pearson

This taught the ML to recognize ones that is clear someone is hitting the prescribed goal even if they are off by a few seconds (usually due to device lag).

Does the ML know what trainer is being used? My thinking is take two smart trainers one with high lag and one with low. Same person on both the recorded output would look different so the ML might treat them differently. My thinking is the ML should try to learn the person not their recordings, so that trends that are the same for a grouping of people could be learned and not assume the people are different just cause their recording is different.

[Nate_Pearson]

@enki42

Does the ML know what trainer is being used? My thinking is take two smart trainers one with high lag and one with low. Same person on both the recorded output would look different so the ML might treat them differently. My thinking is the ML should try to learn the person not their recordings, so that trends that are the same for a grouping of people could be learned and not assume the people are different just cause their recording is different.

We classified a lot of trainers. It should just work and classify correctly no matter what trainer you use.

[D-9]

Great to hear. Thanks, Nate and team!

[SaSha1103]

If you talking about levels. This means the progression level chart and workouts are getting a number right ? I cant wait!!

[Flashpoint51]

@Nate_Pearson

That is very insightful because they are the exact same level .

Damn, this ML is good. It has me validating AT without being in beta yet…

[Nate_Pearson]

@SaSha1103

If you talking about levels. This means the progression level chart and workouts are getting a number right ? I cant wait!!

Levels will be out but the progression chart won’t be out yet.

[roadbiketrevor]

this is so cool.

[SaSha1103]

Hmmm how does one can “live” without the other.
If you know the level of an upcoming workout, but not you current level. You still don’t know if this is achievable,productive or stretch right? Or am I missing something else?