Amazon’s BERT Optimal Subset: 7.9x Faster & 6.3x Smaller Than BERT | Synced

Amazon extracts an optimal subset of architectural parameters for BERT architecture by applying recent breakthroughs in algorithms for neural architecture search.

By · · 1 min read

Source: Synced | AI Technology & Industry Review

Amazon extracts an optimal subset of architectural parameters for BERT architecture by applying recent breakthroughs in algorithms for neural architecture search.