Closed jingweiz closed 7 years ago
This is intended, the reduction is a product for the multiplicative erase and a summation for the additive write. In the paper only one write head was used, but this implementation is more general to facilitate people playing with more write heads for other applications where this might be crucial.
Thanks a lot! That's really helpful!
Hey, So when there're multiple write heads, when writing to memory with these variables:
the
erase
operation is by:then the 2nd dim is reduced by taking a product over this dimension. While for the
write
operation following thiserase
, this 2nd dimention is reduced directly by thematmul
:Is this correct? Cos I didn't get this part from the paper and want to make sure I get it right. Thanks in advance!