https://nalar.dev/tags/model-calibration/ Recent content in Model Calibration on Nalar Hugo en-us Sat, 12 Sep 2026 00:00:00 +0700 https://nalar.dev/calibrate-neural-classifier-confidence-with-temperature-scaling/ Sat, 12 Sep 2026 00:00:00 +0700 https://nalar.dev/calibrate-neural-classifier-confidence-with-temperature-scaling/ <p>A neural classifier can choose the correct class often enough for an application while assigning probabilities that are too concentrated or too diffuse. Accuracy alone does not expose this mismatch. A system that acts differently at confidence thresholds also depends on the numerical probabilities attached to its predictions.</p> <p><strong>Temperature scaling</strong> is a post-training calibration method that adjusts the sharpness of classifier logits with one positive scalar. For a fixed input, it preserves the ordering of logits, so the predicted class remains unchanged when ordinary argmax decoding is used. What changes is the probability distribution produced after softmax.</p>