| Algorithm 1. Pre-Training Matching Network (MN) |
| Input: Data set |
| 1: Initialize MN parameter x |
| 2: For each iteration do |
| 3: Sample training task from the data set, each task includes support set and query set |
| 4: Support set and query set were coded to get G and F |
| 5: Calculate the similarity between G and F |
| 6: Calculate the loss |
| 7: Update the parameters x through Adam optimizer |
Official websites use .gov
A
.gov website belongs to an official
government organization in the United States.
Secure .gov websites use HTTPS
A lock (
) or https:// means you've safely
connected to the .gov website. Share sensitive
information only on official, secure websites.