Perhaps if you needed a larger number of ternary weights, but the paper claims to achieve the same performance with ternary weights as one gets with 16-bit weights using the same parameter count.
Current theme: default
Less Wrong (text)
Less Wrong (link)
Perhaps if you needed a larger number of ternary weights, but the paper claims to achieve the same performance with ternary weights as one gets with 16-bit weights using the same parameter count.