This can work well on some problems, but it has 5 critical limitations.
Stateless .
Unaware of Temporal Structure.
Messy Scaling .
Fixed Sized Inputs
Fixed Sized Outputs .
status
not read
reprioritisations
last reprioritisation on
suggested re-reading day
started reading on
finished reading on
Parent (intermediate) annotation
Open it Limitations of using MLP for sequence predicting This can work well on some problems, but it has 5 critical limitations. Stateless . MLPs learn a fixed function approximation. Any outputs that are conditional on the context of the input sequence must be generalized and frozen into the network weights. Una