Logo BookStack
Search Shelves Books Sign up Log in
Info
Content
research
topic
metalearning
Book Navigation
  • Metalearning

  • Educational Resources about Metalearning

  • Integration of DAML

    • DAML code

    • DAML walkthrough

    • Optimizer filter notes

    • Gameplan

    • Status tracker

  • Integration of multi-task code in allennlp

    • Info

  • Testing

    • Tests I need

  • Repo cleanup notes

  • Design notes 5-27

Books
Metalearning
Integration of DAML

Integration of DAML

This describes efforts to work on integration of DAML into the existing content scoring pipeline
https://github.com/qbetterk/DAML

DAML code

import torch import random import numpy as np from config import global_config as cfg from re...

DAML walkthrough

The main point of interest is train_maml in model.py. prev_min_loss gets set to a high value on ...

Optimizer filter notes

The DAML implementation uses this filter when constructing the optimizer Adam(lr = self.meta_lr, ...

Gameplan

Done Switch optimizer over to the ifltered optimizer. todo determine if self.model needs to be m...

Status tracker

2-21-2020: Finished a bunch of updates to the outer loop of maml to make it better reflect the d...

Search Results

Clear Search
Details
Created 5 years ago by kenneth
Updated 5 years ago by kenneth
Actions


Export
  • Contained Web File .html
  • PDF File .pdf
  • Plain Text File .txt
Back to top