Decoder Calibration is the process of aligning the output probabilities or scores of a model’s decoder stage with true likelihoods observed in data. It ensures that model confidence values correspond accurately to actual prediction correctness. Calibration is important for reliable decision-making in machine translation, speech recognition, and classification systems. Researchers evaluate techniques such as temperature scaling and isotonic regression to improve consistency. Accurate decoder calibration contributes to more interpretable and trustworthy AI systems.
We introduce anchor vectors to monitor Rayleigh-backscattering variability in a fiber-optic computing system that performs nonlinear random projection for image classification. With a ~0.4-s calibration interval, system stability can be maintained with a linear decoder, achieving an average accuracy of 80%-90%.
Princeton Office
4 Independence Way, Suite 200
Princeton, NJ 08540
+1 609-520-1555
San Jose Office
2033 Gateway Place, Suite 200
San Jose, CA 95110
+1 408-863-6007
NEC Laboratories America, Inc. (NEC Labs) is the US-based center for NEC Corporation’s global network of corporate research laboratories. Our diverse research groups collaborate with industry, academia and governments to provide disruptive solutions to complex problems. A leader in the integration of IT and network technologies with more than 100 years of expertise, NEC provides a combination of products and solutions that cross-utilize the company’s experience and global resources to meet the complex and ever-changing needs of its customers.