our training procedure is based on a simple machine learning principle: test and train conditions must match – Vinyals et al., Matching Networks for One-Shot Learning
our training procedure is based on a simple machine learning principle: test and train conditions must match
– Vinyals et al., Matching Networks for One-Shot Learning
SGD
It's easy to integrate different libraries in Julia because of common interfaces and shared data structures
Julia
However, comparing with other machine learning community such as Python, it's not matured and stable
Python