Is anyone using neural networks for anomaly detection in observability? If so, which model and how many metrics are you supporting per core?
TimesFM: Time Series Foundation Model for time-series forecasting
21–30 of 123 posts
Re: TimesFM: Time Series Foundation Model for time-series forecasting
#22Seems like a pretty small (low latency) model. Would be interesting to hook up to mouse input (x and y) and see how well it predicts where I’m gonna move the mouse (maybe with and without seeing the predicted path)
Curious George here: why are you trying to predict where the mouse is going? :)
Game developers are constantly trying to minimize lag. I have no idea if computers are so fast these days that it is a "solved" problem, but I knew a game developer ages ago who used a predictive mouse model to reduce the apparent lag by guessing where the mouse would be at the time the frame was displayed (considering it took 30 ms or whatever to render the frame).
Re: TimesFM: Time Series Foundation Model for time-series forecasting
#23Is anyone using neural networks for anomaly detection in observability? If so, which model and how many metrics are you supporting per core?
LSTM is common for this.
Re: TimesFM: Time Series Foundation Model for time-series forecasting
#24Earlier quoted context omitted.
I imagine they're both worse than good old exponential smoothing or SARIMAX.
Depends on use case. Hybrid approaches have been dominating the M-Competitions, but there are generally small percentage differences in variance of statistical models vs machine learning models. And exponentially higher cost for ML models.
At the end of the day, if training or doing inference on the ML model is massively more costly in time or compute, you'll iterate much less with it.
I also think it's a dead end to try to have foundation models for "time series" - it's a class of data! Like when people tried to have foundation models for any general graph type.
You could make foundation models for data within that type - eg. meteorological time series, or social network graphs. But for the abstract class type it seems like a dead end.
Re: TimesFM: Time Series Foundation Model for time-series forecasting
#25Is anyone using neural networks for anomaly detection in observability? If so, which model and how many metrics are you supporting per core?
What do you mean by “observability”?
Re: TimesFM: Time Series Foundation Model for time-series forecasting
#26I'm curious why we seem convinced that this is a task that is possible or something worthy of investigation. I've worked on language models since 2018, even then it was obvious why language was a useful and transferable task. I do not at all feel the same way about general univariate time series that could have any underlying process.
+1 for “any underlying process”. It would be interesting what use case they had in mind.
Re: TimesFM: Time Series Foundation Model for time-series forecasting
#27Is anyone using neural networks for anomaly detection in observability? If so, which model and how many metrics are you supporting per core?
What do you mean by “observability”?
Telemetry. Dashboards. The application is knowing when a signal is anomalous.
Re: TimesFM: Time Series Foundation Model for time-series forecasting
#28"Time series" is such an over-subscribed term. What sorts of time series is this actually useful for? For instance, will it be able to predict dynamics for a machine with thousands of sensors?
Even if it was for multivariate time series, the model would first need to infer what machine are we talking about, then its working conditions, and only then make a reasonable forecast based on an hypothesis of its dynamics. I don’t know, seems pretty hard.
Re: TimesFM: Time Series Foundation Model for time-series forecasting
#29Earlier quoted context omitted.
Curious George here: why are you trying to predict where the mouse is going? :)
Game developers are constantly trying to minimize lag. I have no idea if computers are so fast these days that it is a "solved" problem, but I knew a game developer ages ago who used a predictive mouse model to reduce the apparent lag by guessing where the mouse would be at the time the frame was displayed (considering it took 30 ms or whatever to render the frame).
The only thing worse than lag is uneven lag, which is what you're going to end up with. Constant lag can be dealt with by players, jitter can't.
Re: TimesFM: Time Series Foundation Model for time-series forecasting
#30Earlier quoted context omitted.
What do you mean by “observability”?
Telemetry. Dashboards. The application is knowing when a signal is anomalous. https://en.wikipedia.org/wiki/Observability_(software)
Oh, yes I am working on that. Usually LSTM, exploring encoder-decoders and generative models, but also some simpler models based on periodic averages (which are surprisingly useful in some use cases). But I don’t have per-core metrics.