NCTV: Neural Clamping Toolkit and Visualization for Neural Network Calibration

by   Lei Hsiung, et al.
The Chinese University of Hong Kong

With the advancement of deep learning technology, neural networks have demonstrated their excellent ability to provide accurate predictions in many tasks. However, a lack of consideration for neural network calibration will not gain trust from humans, even for high-accuracy models. In this regard, the gap between the confidence of the model's predictions and the actual correctness likelihood must be bridged to derive a well-calibrated model. In this paper, we introduce the Neural Clamping Toolkit, the first open-source framework designed to help developers employ state-of-the-art model-agnostic calibrated models. Furthermore, we provide animations and interactive sections in the demonstration to familiarize researchers with calibration in neural networks. A Colab tutorial on utilizing our toolkit is also introduced.


page 1

page 2


Calibration of Neural Networks

Neural networks solving real-world problems are often required not only ...

Deep Learning Tools for Audacity: Helping Researchers Expand the Artist's Toolkit

We present a software framework that integrates neural networks into the...

Calibrating Deep Neural Networks using Focal Loss

Miscalibration – a mismatch between a model's confidence and its correct...

Deep Kernel Learning for Mortality Prediction in the Face of Temporal Shift

Neural models, with their ability to provide novel representations, have...

Linguistic calibration through metacognition: aligning dialogue agent responses with expected correctness

Open-domain dialogue agents have vastly improved, but still confidently ...

Improving Uncertainty Calibration via Prior Augmented Data

Neural networks have proven successful at learning from complex data dis...

Greenformer: Factorization Toolkit for Efficient Deep Neural Networks

While the recent advances in deep neural networks (DNN) bring remarkable...

Please sign up or login with your details

Forgot password? Click here to reset