AI FTP detection is smarter than AT

Even without AT, just having a quantitative measure of how much harder one workout is compared to another has significantly improved my training. Of course, you should never leave your brain at the door and use things blindly. E. g. I cannot directly compare VO2max workouts like versions of Spanish Needle with steady state VO2max workouts, I might be better at the former than the latter. But still, it is hugely helpful.

2 Likes

For what it’s worth, from their description it doesn’t seem like AT is one single model anyways. It’s probably a few models underneath, such as one for predicting progress levels and another to predict long term outcomes.

Look at the problem they want to solve: they started with training plans that were often too hard and led to burn outs and demotivated users. It seems like AT is definitely biased for making things as easy as possible while maintaining good outcome. With that criteria in mind, I think it’s been great to most users.

So perhaps when it errs, it makes some workouts too easy, but that’s hard to objectively measure. Especially when the outcome is just supposed to be better fitness. Perhaps not pushing every workout to the limit is by design, certainly if I can get the same adaptions I’d prefer it easier.

1 Like

Please don’t put words in my mouth. Of course, I don’t think that, and I never wrote that.

Yes, which is why applying ML is difficult and fraught with risks. Even independently of what techniques you use, you want distill some essential information from a whole host of data. Deciding which metrics are important and which aren’t is key.

For example, as best as I can tell, the purpose behind PLs is not to quantify performance, but to select workouts and achieve progressive overload at prescribed rates. I suspect this is the reason why TR hasn’t done much with them yet (at least publicly). For this limited purpose, PLs work well for me even without AT.

Of course, this means AT’s functionality is quite limited at present, and I am missing good analysis tools to judge my progress.

I’m not quite sure what you mean. Yes, the public version of AT cannot ingest unstructured rides at present. But I struggle to understand the rest of the sentences.

Can you be more precise? What can multiple programs predict currently? And from what data?

Yes, and? TTE is not necessarily a relevant measure. For shorter VO2max and higher efforts, you might want repeatability and rather than TTE. Certain smart watches also estimate your VO2max. But what does that number tell you? How does it inform your training? Ditto for TTE? Why should I care, i. e. how does it relate to performance outcomes that are relevant to me?

To be honest, that’s one important issue we haven’t talked about in this thread at all: what information do you expose to the user? I have ranted about TR’s poor performance analysis tools in several other threads (e. g. here), but I understand the problem isn’t simple.

Basically, people can only track a few metrics, and it is the choice of metrics that is the tricky bit. This is really where a good coach can help an athlete: they find out where the strengths and weaknesses lie, what the athlete wants (e. g. be good at a certain cycling discipline) and then weigh whether to focus on strengths or weaknesses (limiters). TR could (and should) take a stab at this, but simply predicting numbers from data might not be helpful at all.

Ideally, I want that TR analyzes an athlete’s past performance, identifies strengths and weaknesses and tells athletes what a particular plan emphasizes. Athletes should know why they should track certain numbers (and not others). Perhaps it does surface TTE as a metric for people choosing the 40k TT plan or the tri plan. But it exposes other metrics to athletes from other disciplines.

I completely agree, and I wrote as much above. End users don’t care whether “the computer” got the result by a traditional algorithm written by a human, an ML-based algorithm or a weegee board.

ML should also be used with a lot of caution. If you listen to the talk I linked to, a vast part of the research was to ensure that the algorithms were not biased — i. e. it reconstructs what we expect the event horizon of a black hole looks like because we want to see a reconstructed image of a black hole.

I know full well it is not a panacea: Amazon used ML carelessly when pre-screening applications: they trained their algorithms to reproduce sexist bias, where e. g. being a member of a women’s chess club was counted as a negative. Another one is Google’s image recognition snafu, they apparently had too few (or no) black people in their training set and black people were categorized as gorillas. I also don’t quite like if colleagues cannot answer what ML did to their data and why it was necessary.

However, treading carefully and resisting the urge to simply produce numbers (e. g. TTE or whatever other metric you want) without thinking about whether this is useful for the user and in what way it is useful seem like good ideas.

Most likely. From what I remember, they have a Quantifier that judges how hard workouts of different energy zones are, although if memory serves there was some human input as well. So in this sense it is also a matter of semantics whether AI FTP is just a feature of AT or not.

What is smarter or best is in the eye of the beholder. Four years ago I figured out how to do my own FTP detection, and then I bought a Garmin 530 in 2019 and the ML stuff using HRV, HR, and power has also been surprisingly valuable and useful. If you’ve never done FTP estimation to set sweet spot and threshold intervals, then AI FTP is an eye opener.

The other part of this discussion is getting into AT/ML vs physiology models. I’m all ears for the day that AT understands that I need more aerobic base development, that I respond better to more endurance work (vs SSB), and that I respond better to certain types of intervals. The physiology models provide metrics/data to inform these type of training decisions. If you are interested in physiology modes, perhaps watch a few key WKO webinars on YouTube (go hit up the WKO thread for recommendations).

4 Likes

Not always. I think you could in principle benchmark the different approaches very easily, there is nothing subjective about them. It’s just that the different companies wouldn’t want to let you do that (at least with an N value that makes your results matter).

FTP estimation is for me a non-issue: once you get into the habit of validating your FTP (as necessary), it doesn’t really matter how FTP is determined, whether the baseline is suggested by eFTP, AI FTP, a ramp test or a 20-minute test. Perhaps that’s why I am personally not wowed by AI FTP or algorithms by competitors that do the same. It seems to me that rather than finding the perfect algorithm or testing methodology, I’d rather verify and be done with it. Certainly seems easier than a multistep FTP testing protocol or cooking up my own FTP estimator. (Still, I can very much appreciate that you rolled your own :sunglasses:)

But I can see that it is a good feature for the broader masses, especially people who don’t yet know what all-out feels like. (I think this is something more experienced athletes take for granted.)

Are these mutually exclusive? I don’t see a reason why in the future you can’t combine both.

IMHO the critical missing feature is that AT v4.0 — with athlete/coach input! — selects and surfaces certain key performance metrics. This is also what is missing on all other platforms I have seen (and I do not claim to have seen them all): performance analysis is a bit of a mess. Yes, some will spit out things like estimates for TTE at certain powers, but is that a relevant metric for you? Maybe? But maybe not. Spitting out numbers without knowing how relevant they are for that particular individual means you could flood people with irrelevant numbers.

There has to be some user input, I don’t expect it all to be automatic. E. g. I don’t expect that AT will be able to tell you whether you should focus on a weakness or a strength this season. That is something human coaches are needed for. My current weakness is resilience: I can put out decent power, but I fatigue more quickly than before the month-long hiatus. So I would like to focus on that. This has to be translated into training goals and metrics.

Of course, having the right metrics will also improve AT since you can really optimize the training plan to optimize these metrics (and perhaps some additional metrics under the hood).

AT v7.0 could then give you feedback and make broader changes to your training plan: @WindWarrior, looks like your intensity is too high. I’m going to prescribe you more endurance work and less intensity in the current block, let’s see if that improves things. But IMHO it all starts with choosing the right set of metrics for the various training goals. The first metric to start with is consistency — it is easy to define, easy to implement and independently of your training philosophy, staying consistent is one of the fundamental principles that will make you faster.

I’ll have a look.

At the moment, I am skeptical of physiology models, but remain open-minded. Still, I have signed up for the newsletter of Frank Overton’s HRV-based solution — I love someone knowledgable is trying. There features similar to that (e. g. some Garmin smartwatches will tell you “how full your battery” is and how well you have recovered), which you might use to inform your training. But I am not sure if this is really useful input for making training decisions at this point.

Let me briefly chime in… have been reading thIs largely with interest, mostly because I can follow the TOs comment and idea.
Through the thread, got a bit tired by @OreoCookie ’s long and somewhat – seemingly – overconfident posts, but they did trigger some interesting thoughts and responses;-)

But now it matters how FTP is validated… same issue;-)

Uhm, well, the “subjects” (human beings) are …

But something along the lines of AI-AT should be able to do, for instance, exactly that.
But I am with you, for now we are stuck with ML, which is still conceptionally and effectively much closer to linear regression (pun intended;-) than artificial intelligence…

I am truly looking forward to much improved robots here, and times and current progress are exciting.
However, all this relies not only on software and modeling, it very fundamentally relies on large sets of high quality data “of all kinds”. Including very intimate health data collected with minute detail over very long times.

This very clearly also requires truly new and very much improved approaches to data protection and safety, (temporary and permanent) data ownership, retraction and deletion options, etc. All this in an international setting…

Don’t want to be too pessimistic, we’ll likely halfway figure this out more or less in time, but I don’t see how this is actively worked on in this community yet:-o and without it we will end up with severely dangerous versions of /big brother/ or the brave new world.

1 Like

It is not the same issue, because knowing what being right at lactate threshold feels like is a vital skill when you ride and train. And it isn’t a difficult skill to learn.

In terms of techniques, there is no distinction between “AI-AT” and AT, the AI in AI FTP is a marketing name. Under the hood it uses the exact same techniques as Adaptive Training.

ML is a name for a vast array of techniques, most of which have zero to do with linear regression.
Outside of research, AI is often used interchangeably. For example, Google’s chess engine Alpha Zero is based on machine learning techniques, but is often referred to as AI.

The fundamental problem today with AT is that it is trying to optimize your workout on a specific day, within very tight constraints: it is only allowed to select a workout with similar a Zone focus and roughly the same duration as the one on your schedule. It can’t (doesn’t have the intelligence today?) to fundamentally alter the workout. In addition, AT is constrained by the structure of TR plans:

  • Work to recovery ratio (number of weeks of work compared to rest)
  • Number of days with intensity vs endurance vs active recovery
  • Workout length
  • Etc.

It doesn’t matter how sophisticate or not AT is, it is fundamentally hamstrung by the above constraints. So you can’t make the logical leap that AI FTP detection is using a more sophisticated ML model than AT is using. AT’s model could be super sophisticated, but at the end of the day it is solving a comparably much simpler problem: given how you’ve performed on previous days, and your perceived exertion, should I give you a harder / easy / same workout?

9 Likes

Hard agree. It may be really clever, but it’s solving a problem that isn’t all that difficult. If we as athletes were able to look at our workout performances objectively, we could do the job ourselves easily. It’s “just” a matter of assessing how you laid down the watts and how that felt, and then serving up something of the same flavour but between 20% easier and 20% harder next time.

The main point for me is that for 20 weeks it’s served me up workouts that I’ve consistently nailed (and very much enjoyed in the main) while still progressing me and given me the flexibility to choose something more challenging on days when I get to the bike and feel strong. It’s all good.

6 Likes

QFT.
As a matter of building out functionality of AT, you probably want to start with something whose functionality is quite modest, learn from building it out and optimizing it, and then include more functionality in a revision (e. g. allowing AT to also change volume).

1 Like

Maybe here – in the mutually diverging backgrounds – is the reason for me seeing problems with your posts…?

The rest of this post confirms my opinion about

2 Likes

Completely agree. The more you train outdoors without using TR structured rides … the more useless Progression Levels become. That said, at least FTP seems to remain accurate based on outdoor rides. I simply ignore progression levels this time of year, and pick harder workouts as needed if I train indoors.

3 Likes

Exactly my feelings. At is doing what it was programmed to do, which is to purposefully underestimate the workout, get feedback from the user and then adjust accordingly. I personally dont like the super slow ramp as i can do pl 5 vo2 work almost any time of the year without any prep. I don’t see the point of using at if it doesnt adapt to me and i need to keep manually adjusting workouts.

Tr does have a huge dataset, but also with mostly new riders who adapt to any new stimulus.

5 Likes

I don’t have much faith in AT or AI FTP detection.

I just had 10 days off sick which I flagged in the calender as an illness. Had to remove a B race I had tomorrow as I still feel pretty average.
After removing the race it changed my next workout to a ramptest (yeah… no thanks :nauseated_face: )

So I saw what AI FTP detection was and it gave me a 3W FTP bump. There’s no way after being sick for 10 days would my FTP have improved, it makes zero sense.

I’m sticking to setting my own FTP by feel or testing when I’m actually in the mood for testing.

1 Like

I dont see an issue with what it did. It seems pretty logical. You were off and when you came back it is saying we should retest. You can do a ramp test or use the aiftp amount or not. 3w is not a large change. Who knows if you were not sick what the increase would of been.

If you dont trust aiftp then do the ramp test

1 Like

You reckon it’s logical to gain power after having the flu or covid?? AT can’t tell the difference between a week off riding outside and a week off bed ridden with a virus, despite being able to flag it as illness in the software.

It didn’t say I should retest because I was off sick, It said I should retest because I removed an event from my calendar and recalculated my plan.

I will be doing tests going forward or just setting FTP by feel.

I think the difference is I see you indicating you are ready to start training again. If I had the flu I may or may not be ready to ride strong but if I say I am ready to train how is anyone going to know what to give you other then to advise you to do a ramp test. If I had covid I suspect doing a ramp test would be a good start.

If we get sick and take some time off is our FTP going to plummet and not bounce back quickly? It would likely stay in the same range most of the time. I think we have different expectations on what any software can advise. AIFTP cant tell how sick you are or if you are ready to ride. That is up to you.

I don’t think the prediction is not as illogical as you seem to think it is. Taking a week off is pretty much like a recovery week, and assuming you are healthy you do get fitter during a recovery week. However, the algorithm probably doesn’t know that you were sick (not sure whether indicating you are sick in TR’s calendar makes a difference) and how sick you were.

A difference of 3 W is likely negligible, and I’d just try and see how that works for you.

1 Like

Thats what I’m saying, AT and AI ftp detection can’t tell the difference between a recovery week and a week off ill.

I was pretty sick and I’m only easing back into things with endurance rides, the last thing I want to do right now is a ramp test.

I’d hoped AI ftp detection could help me set a workable FTP recognising the 10 illness days I put in the calendar.

I like Trainerroad, the workout library, calender and workout player are all great but I think AT and AI FTP detection is very much still in a beta stage.

I’m really confused: you don’t have to do a ramp test. If you are on the mend and feel that you shouldn’t do workouts with intensity, then do that. And then either reassess your FTP or see what AI FTP thinks in a week or two when you feel ready to train. I reckon that if you haven’t done workouts with intensity for three weeks or longer, AI FTP will lower your FTP.

IMHO the issue isn’t that AI FTP is in beta, it is that you don’t trust it, because you don’t understand what it does.

When I was let into the public beta for AT, initially I would often override AT, adding a bit of intensity here, take back adaptations I thought were non-sensical, yet did not change others. It was a mess and didn’t work well. Once I started trusting AT more and understood its weaknesses and how it worked under the hood, things got much better. I don’t trust it blindly, but I also know that if I mess with it too much, the outcome is worse overall.

You write that AI FTP doesn’t take sick time into account. I don’t know whether that is true, but it wouldn’t surprise me. After all sick ≠ sick, breaking a rib is different from catching Covid.

I’d just let AI FTP reassess when you are ready. Start with that as a baseline and see how you fare.