Time series benchmark problems found in the literature ... are often conceptually simpler than many tasks already solved by LSTM. They often do not require RNNs at all, because all relevant information about the next event is conveyed by [...] contained within a small time window. — Applying LSTM to Time Series Predictable through Time-Window Approaches, 2001
Answer
a few recent events
status
not learned
measured difficulty
37% [default]
last interval [days]
repetition number in this series
0
memorised on
scheduled repetition
scheduled repetition interval
last repetition or drill
Parent (intermediate) annotation
Open it literature ... are often conceptually simpler than many tasks already solved by LSTM. They often do not require RNNs at all, because all relevant information about the next event is conveyed by <span>a few recent events contained within a small time window. — Applying LSTM to Time Series Predictable through Time-Window Approaches, 2001 <span>