Skip to content

Calibrating neural networks with Bayesian nonparametric regression (Inferno) to quantify uncertainty and improve prediction reliability.

active 2024-11-112025-04-18 (UTC)

Complete coverage26,532 / 26,532 hourly files (100%) · 2 absent upstream2023-08-152026-08-24 (UTC)
Events
199
Pushes
78
Pull requests
19
Issues
69
Stars
1
Forks
0

Activity over time

Daily event counts in the loaded window

Line chart, 159 days from 2024-11-11 to 2025-04-18. Pushes: 78 total, peak 10 in a day. Pull requests: 19 total, peak 8 in a day. Issues: 69 total, peak 25 in a day. Comments: 5 total, peak 2 in a day. Stars: 1 total, peak 1 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.

Top contributors

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

ContributorContributionsPushesPRsComments
58966416471195
pglpm7700

Recent activity

Latest issues, pull requests and releases

  • Issue#265896642025-04-17 20:58
    update readme with basics
  • Issue#565896642025-04-17 20:58
    update python to 3.12.10 and check if py project runs smooth with installations
  • Issue#555896642025-04-16 22:39
    update the license file to more appropriate for project
  • Issue#545896642025-04-16 22:38
    plots comparing CNN and inferno (sigmoid confidence vs. true probs)
  • Issue#535896642025-04-16 22:37
    make prediction pipeline img + aux data -> CNN -> inferno -> prediction
  • Issue#85896642025-04-16 22:35
    setup and fetch the project on remote server
  • Issue#305896642025-04-16 22:35
    rewrite all to classes (easier to maintain)
  • Issue#395896642025-04-16 22:35
    define model name input prompt/config
  • Issue#235896642025-04-16 22:35
    introduce early stopping
  • Issue#195896642025-04-16 22:34
    figure out how optimizer works
  • Issue#115896642025-04-16 22:34
    introduce dropout layers
  • Issue#385896642025-04-16 22:34
    convert the printouts to rich console
  • Issue#425896642025-04-16 22:34
    default values if config is missing
  • Issue#415896642025-04-16 22:34
    introduce dataset param relation in %
  • Issue#435896642025-04-16 22:34
    introduce testing of the models
  • Issue#465896642025-04-16 22:34
    introduce GPU stats monitoring in console
  • Issue#445896642025-04-16 22:34
    update statistics printout of Dataloader
  • Pull request#525896642025-04-09 21:14
  • Issue#495896642025-01-14 18:50
    introduce dropout rate
  • Pull request#515896642025-01-14 18:50
  • Pull request#515896642025-01-14 18:50
  • Issue#505896642024-11-26 15:19
    look into f1 rate by balancing dataset for training & validation
  • Issue#495896642024-11-26 00:41
    introduce dropout rate
  • Issue#485896642024-11-23 21:28
    update repository tags
  • Issue#475896642024-11-23 21:21
    remote automation

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.