- Curriculum Learning - When training machine learning models, start with easier subtasks and gradually increase the difficulty level of the tasks.
- Motivation comes from the observation that humans and animals seem to learn better when trained with a curriculum like a strategy.
- Link to the paper.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/local/bin/python3 | |
""" | |
store and check items in a bloom filter | |
limitations: | |
- not optimized for speed. | |
- data structures on disk are not protected from multiple writers... so, use accordingly. | |
- some other rough edges... under development. example: no quiet option. | |
- mixing conventional bloom filter and vector treatment complicates things somewhat. |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Think Distributed Systems Summer School | |
Providence, RI | |
Curriculum | |
Friday (night session, open discussion) | |
* Background, introductions | |
* What are you working on in distributed systems? | |
* Lightning talks on research or open problems |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import threading | |
# Based on tornado.ioloop.IOLoop.instance() approach. | |
# See https://github.com/facebook/tornado | |
class SingletonMixin(object): | |
__singleton_lock = threading.Lock() | |
__singleton_instance = None | |
@classmethod |