Catatan bukti metode

Model Calibration

Model calibration is a post-hoc technique that adjusts the probability outputs of a trained classifier so that predicted confidence scores match empirical outcome frequencies. A classifier is said to be perfectly calibrated if, among all predictions made with confidence p, exactly a fraction p of them are correct. Systematic miscalibration of modern deep neural networks was rigorously documented by Guo et al. (2017), who showed that networks trained with standard cross-entropy loss tend to be overconfident, and proposed temperature scaling as a simple, effective remedy.

Sources recorded, not reviewed

Catatan sumber

Kutipan disalin apa adanya dari catatan sumber metode. Tidak ada verifikasi tingkat klaim yang disimpulkan darinya.

Probability Calibration of Classifiers

Catatan metode taksonomi · ml-model / machine-learning

Guo, C., Pleiss, G., Sun, Y., & Weinberger, K. Q. (2017). On calibration of modern neural networks. International Conference on Machine Learning, 1321–1330. · URL

Buka metode lengkap

Klaim yang dikurasi

Klaim tersimpan dalam buku besar bukti, masing-masing dengan penilaiannya sendiri.

Belum ada klaim yang dikurasi

Tampilan ini tidak menciptakan penilaian klaim ketika buku besar tidak memilikinya.

Metode terkait

Dihasilkan dari grafik metode dan ditampilkan sebagai relasi yang disarankan mesin — tidak ada klaim bukti yang disimpulkan.

Taxonomic bucketConformal Predictionmachine-suggested · Relational suggestion, not evidence.See alsoLogistic Regressionmachine-suggested · Relational suggestion, not evidence.See alsoUncertainty Quantificationmachine-suggested · Relational suggestion, not evidence.