Skip to content

vipulSharma18/Exploration-For-Shortcut-Learning

View on GitHub ↗Related repositories →

Features used by ANNs often differ from humans, they prefer more available features (pixel footprint) even if they are less or similarly predictive as the core ones. The project uses exploration & bandits to guide a supervised learning algo to attend to the core features instead of the spurious ones.

active 2024-04-29 → 2024-05-12 (UTC)

Complete coverage28,111 / 28,111 hourly files (100%) · 2 absent upstream2023-08-15 → 2026-10-29 (UTC)
Events
75
Pushes
72
Pull requests
0
Issues
0
Stars
1
Forks
0

Activity over time

Daily event counts in the loaded window

Line chart, 14 days from 2024-04-29 to 2024-05-12. Pushes: 72 total, peak 12 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 0 total, peak 0 in a day. Comments: 0 total, peak 0 in a day. Stars: 1 total, peak 1 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

ContributorContributionsPushesPRsComments
vipulSharma18727200

Recent activity

Latest issues, pull requests and releases

No issue or PR events — this repo's activity is pushes only.

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 1 stars here means stars gained during the window, not the repo's star count.