Slumbering to Precision: Enhancing Artificial Neural Network Calibration Through Sleep-like Processes

Jean Erik Delanois; Aditya Ahuja; Giri P. Krishnan; Maxim Bazhenov

cs.LGMar 9, 2026

Slumbering to Precision: Enhancing Artificial Neural Network Calibration Through Sleep-like Processes

Authors: Jean Erik Delanois, Aditya Ahuja, Giri P. Krishnan, Maxim Bazhenov

Organizations: Department of Computer Science & Engineering, University of California, San Diego, La Jolla, California, USA · Department of Medicine, University of California, San Diego, La Jolla, California, USA · ARTISAN, Georgia Institute of Technology, Atlanta, Georgia, USA

Abstract

Artificial neural networks are often overconfident, undermining trust because their predicted probabilities do not match actual accuracy. Inspired by biological sleep and the role of spontaneous replay in memory and learning, we introduce Sleep Replay Consolidation (SRC), a novel calibration approach. SRC is a post-training, sleep-like phase that selectively replays internal representations to update network weights and improve calibration without supervised retraining. Across multiple experiments, SRC is competitive with and complementary to standard approaches such as temperature scaling. Combining SRC with temperature scaling achieves the best Brier score and entropy trade-offs for AlexNet and VGG19. These results show that SRC provides a fundamentally novel approach to improving neural network calibration. SRC-based calibration offers a practical path toward more trustworthy confidence estimates and narrows the gap between human-like uncertainty handling and modern deep networks.

Figures & tables

	Accuracy	ECE	NLL	Brier	Entropy
ResNet 152 on CIFAR 100
Baseline	84.9	0.062184	0.601612	9.369636	0.457585
Baseline + SRC	84.8	0.012978	0.570327	4.33612	1.015678
Baseline + TS	84.9	0.016904	0.562992	5.478358	0.838229
Baseline + SRC + TS	84.8	0.014159	0.565073	4.940667	0.857810
Baseline + LS	85.2 †	0.026636	0.617318	1.624467 †	1.162224 †

Table 1: Accuracy and calibration metrics averaged over 10 trials (STD in Appendix B). Bold values indicate the best-performing post-hoc method. Bold values marked with ( † ) indicate methods that achieved the best score but required retraining.

Figure 1: Reliability diagrams showing improvement in ECE metric as a result of SRC (Right) after initial Baseline training (Left) for the ResNet-152 model trained on CIFAR-100. Confidence more accurately reflects accuracy (blue bins closer to diagonal). Red bars indicate difference between ideal and actual accuracy. Test confidence and accuracy are shown.

Panel of Figure 2 — Figure 2: Two-dimensional histograms of ResNet-152 confidences on CIFAR-100 baseline confidence (horizontal) vs method confidence (vertical); color encodes sample density and the red diagonal marks no change. SRC (left) increases or decreases confidences; TS (right) only maintains or reduces them.

Figure 3: Histograms of FF feature magnitudes for ResNet-152 on CIFAR-100: Baseline/TS (blue), SRC (orange), and LS (green). The Baseline model shows the widest distribution (0–8), LS is more constrained (0–4.5), and SRC shifts the Baseline distribution to a lower maximum (5.5), closely matching LS. This suggests SRC aligns feature representations with the well-calibrated LS model without full retraining.

Figure 4: Distributions of nonzero FF layer elements over test samples in ResNet-152 on CIFAR-100 for Baseline/TS (blue), SRC (orange), and LS (green). Baseline representations are densest (82–90% nonzero) and LS is moderately sparser with partial overlap. SRC achieves substantially sparser representations (67–81%).

Figure 5: Weight changes from SRC for ResNet-152 on CIFAR-100. Most weights decreased, leading to smaller feature magnitudes (similar to LS) and sparser representations.

Appendix figures & tables2 assets

Supplementary material from the paper’s appendix.

Appendix

	Accuracy	ECE	NLL	Brier	Entropy
CIFAR 100
baseline	0.0000	0.000000	0.000000	0.000000	0.000000
baseline + SRC	0.0583	0.000928	0.000575	0.026980	0.008026
baseline + TS	0.0000	0.000003	0.000000	0.000178	0.000033
baseline + SRC + TS	0.0583	0.000692	0.000387	0.004049	0.000727
baseline + LS	0.1078	0.002367	0.005212	0.016566	0.019289

Appendix

Table 2: Standard deviations across 10 trials

Simulation	Time Steps	dt	Decay Rate	Max Spiking RateRate	Postive STDP	Negative STDP	Spiking Thresholds
ResNet 152 CIFAR 100 SRC	443	0.001	0.9521040578368124	299.64109973100756	0.000716159191361385	-0.00046873584104501213	[18.08956309358943, 20.4728432017464, 17.0355215370257]
ResNet 152 CIFAR 100 SRC TS	443	0.001	0.9521040578368124	299.64109973100756	0.000716159191361385	-0.00046873584104501213	[18.08956309358943, 20.4728432017464, 17.0355215370257]
ImageNet AlexNet SRC	492	0.001	0.9836698145272654	96.77346924873888	0.00017228598853676435	-0.0003060770957571102	[0.3969962502366198, 19.801537664023588, 17.8318793443642]
ImageNet AlexNet SRC TS	492	0.001	0.9836698145272654	96.77346924873888	0.00017228598853676435	-0.0003060770957571102	[0.3969962502366198, 19.801537664023588, 17.8318793443642]
ImageNet GoogLeNet SRC	297	0.001	0.9230026016980454	57.69634835829613	4.994787627593506e-05	-0.0009992231413448339	[1.061303932245, 1.0, 1.0]
ImageNet GoogLeNet SRC TS	297	0.001	0.9230026016980454	57.69634835829613	4.994787627593506e-05	-0.0009992231413448339	[1.061303932245, 1.0, 1.0]

Appendix

Table 3: Sleep hyperparameters for each simulation.

Model Calibration

Model calibration aligns predicted confidence or model outputs with observed outcomes and measurements to support more reliable decisions.

See all 214 papers

Calibration in One Go: Jointly Learning Accurate and Calibrated Neural Networks
Oct 9, 2026Nektarios Kalampalikis, Pablo M. Olmos, Isabel ValeraModel Calibration Post-Hoc Calibration
Dept. of Computer Science Saarland University, Germany
Enhancing Deep Neural Network Reliability with Refinement and Calibration
May 22, 2026Ramya Hebbalaguppe, Ajay Shastry, Soumya Suvra Ghosal +1Probability Calibration Uncertainty Calibration
SIT, Indian Institute of Technology Delhi, New Delhi, India
Neighborhood Smoothing for Calibration
Oct 6, 2026Idan Horowitz, Avigdor GalModel Calibration
Faculty of Data and Decision Sciences Technion Haifa, 3200003, IL

Oct 9, 2026J/K move · Enter open · S save

Calibration in One Go: Jointly Learning Accurate and Calibrated Neural Networks

Nektarios Kalampalikis, Pablo M. Olmos, Isabel Valera

Dept. of Computer Science Saarland University, Germany

Model Calibration Post-Hoc Calibration

Open paper AskPDF arXiv

Neural networks (NNs), while highly flexible and versatile, are often poorly calibrated. Post-hoc calibration methods adjust the outputs of an already trained model using a separate calibration dataset and additional calibration parameters. This process adds overhead that requires separate optimization of the calibrator and subsequent model selection. In this paper, we show that standard (post-hoc) calibrators can be trained end-to-end with the backbone via a bilevel Stackelberg formulation. This formulation eliminates the need for a separate calibration set or a dedicated calibration loss by jointly optimizing accuracy and calibration using cross-entropy, introducing only one additional hyperparameter: the calibrator learning rate. Although our framework supports calibrators ranging from temperature and matrix scaling to NN layers, our results show that using the final classification layer itself as the calibrator yields accurate, well-calibrated models with no additional parameters. Our approach outperforms SOTA calibrators with minimal added complexity, while also avoiding the multiplicative overhead of separate calibration components in settings such as multi-task learning.

Abstract

Model Calibration

Explore similar work

Calibration in One Go: Jointly Learning Accurate and Calibrated Neural Networks

Enhancing Deep Neural Network Reliability with Refinement and Calibration

Neighborhood Smoothing for Calibration