Thatās ok I do too. I was just confused about what the point we were debating was.
YES!
@ambermalika @Nate_Pearson
As suspected the FTPd was off. On initial rollout it appeared accurate at 317. However after week 3 & 4 of SusPBHV1 the FTPd kept decreasing and this morning it said 313. If it was still 317 I would have probably skipped the Ramp Test.
Maybe 2.3% difference (313 vs 320) is within the acceptable margin, but FTPd as of now seems not quite dialed.
It wasnāt meant to be shown daily. Weāre likely going to put a 14-day gate on it so you can only see it once per 14 days.
Hereās the thought right now:
Show you your FTP, and then show that for the next 14 days anytime you click that button whether you accepted it or not. Weād tell you when you can see your new FTP.
The goal is to get you into the right workouts for you, so that you get faster, and crush your enemies.
Itās the combination of Ramp Test + Progression Levels that makes this powerful.
I understand. Just cannot resist the urge to reverse engineer what the AI has distilled.
hahaā¦we need to form an official TR red team for rollouts. I want onā¦
I would imagine that Machine Learning makes this almost impossible but IANAS
Where I would expect AI to be hard to predict will be in outlier scenarios. But consistently following a standard plan should (might) have a simple low dimensional model (with reduced accuracy). E.g. something roughly linear week-to week within a block, but with different slopes for different blocks/people. And maybe noise or asymptotes within a week. Or maybe it would have been mostly flat with the big change happening in recovery week. Admittedly neither seems a good match for the limited data here.
I have been checking my FTP detection over my recovery week and seeing it provide 286/287 depending on the day. Given I am starting a specialty block this week I thought I would hit the ramp test today, particularly since it is 10 more weeks before a ramp test is back on my calendar. Seeing this within 1% gives me confidence, disappointing as I thought the AI number might have been low, but it is moving in the right direction so I am happy.
Admittedly, I kind of like to suffer, so look forward to the ramp tests!
Iām sure there is coherence in the output, but itās just on a longer time scale compared to short time windows where noise is created by model over-fitting.
It seems like you really get this stuff, @jjmc.
Overfitting is one of the main issues that we were aware of when we built this. (Overfitting is when our model exactly learns what it was trained on.)
IE, if we just used SSBLV as training data, then it would likely pick up such a big signal from that data set that weād āoverfitā the data and have a model that doesnāt work super well.
Weāre really lucky in that we can pull complete histories of training data. So we get someoneās entire career including the time before there was even indoor training, a time when they pause their TR subscription, a time when they do just one custom workout a week and 1 race per week, etc.
But even with all that, we can overfit the data if weāre not careful.
What we really want to see is how the FTPD is doing over 3-6 week periods when folks are having high compliance and consistency with an AT plan. If numbers are dropping off of that, it will be a natural question as to if that is legit or an issue.
Yes, and we donāt even have to wait that long. We can look at the next workout outcomes and survey responses. IE if everyone failed their next workout OR everyone marks their next workout with a lower RPE compared to those who didnāt do AI FTP Detection then weāve got work to do.
The opposite is true too. If we get a higher pass rate and RPE survey responses that we think are appropriate for the workoutās PLs, then weāve likely improved things and should push forward.
This isnāt quite accurate. I wouldnāt say āaverage riderā.
You do make a good point though. If youāre a high or low tester, you should probably get a more āaccurateā result for AI FTP Detection compared to the ramp test.
And by āaccurateā, I mean getting you into the appropriate workouts to make you faster.
Just sharing:
Starting SSBBLV1 today after a couple of rounds of Pol Base and did the FTP detection.
I got nothing.
I mean that literally. 0 watts.
Itās okay though. I was kinda hoping for that anyway.
Completely agree.
YOU donāt have to wait that longā¦but us āred teamersā without insider knowledge have to wait longer!
From the quotes that indicate āpersonal biometrics like ageā are taken into account, I deduce that segmentation along other variables (such as age) is also fed to the model. So indeed not an āaverage riderā, but an average of those sharing the same biometrics.
Iām just guessing at the contents of a black box.
You are correct. And the farther you go out the less certain we can be. Another limitation with the current approach is we are assuming youāre going to do the work.
We are going to try to make it so we can figure out how likely you are to actually do the work, which would be like .
So when we first launch AI FTP Prediction weāll need to tell people to use a bit of constraint. Butā¦whatās also interesting is the model doesnāt always give you a higher FTP if you have more work planned.
I just want to say, I love this!
While the ācrushing enemiesā part is entertaining, itās the āget you into the right workoutsā thatās money.
This^
This was my thought/personal experience so far.