Hacker News new | past | comments | ask | show | jobs | submit login

Yes the bulk of our business is time series. This includes everything from hardware break downs to fraud detection. I think Jeremy has some good points but in general, but I wouldn't assume that everything is binary. (By this, I mean look at these kinds of terse statements with a bit of nuance)

Usually as long as you have a high amount of regularization and use truncated backprop through time in training you can learn some fairly useful classification and forecasting problems.

Beyond that standard neural net tuning applies. Eg: normalize your data, pay attention to your weight initialization, understand what loss function you're using,..




So if LSTMs are purposely forgetting, do you need less training data than a CNN?


LSTMs don't "forget" more than "remember the things that matter". They don't necessarily need less data. They do have a limit on the "length" of time steps they can handle though. Eg: You can't do thousands in to the future (maybe a few hundred or so)

The long part of "LSTM" means remember good long ranging dependencies.




Consider applying for YC's Spring batch! Applications are open till Feb 11.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: