On Getting Confidence Estimates from Neural Networks | Bharath's notes
I've been reading on and off about this topic for a while now, and it comes up very often in applied ML. How confident is the neural network about a particular prediction it makes? Can we switch to a different end user experience when the network is not confident? In a typical scenario, a model is trained on a limited dataset and gets deployed in a product, where unless the user experience is strictly guarded, the model will get hit with inputs that were not anticipated. This is the problem of Out-Of-Distribution (OOD) detection - and if a model can either say that it does not "know" what to do in such cases, or equivalently, make a low confidence prediction - then that is useful for avoiding catastrophic failures. There is a lot of research that focuses on this topic, and what follows is a summary of some of the papers I've read. So how do we measure the confidence of a neural network? The majority of research focuses on Classification models, so we'll talk about them first, with a se
I've been reading on and off about this topic for a while now, and it comes up very often in applied ML. How confident is the neural network about a particular prediction it makes? Can we switch to a different end user experience when the network is not confident? In a typical scenario, a model is trained on a limited dataset and gets deployed in a product, where unless the user experience is strictly guarded, the model will get hit with inputs that were not anticipated. This is the problem of Out-Of-Distribution (OOD) detection - and if a model can either say that it does not "know" what to d
saved by
related reading
- On Calibration of Modern Neural Networksarxiv.org
- [1706.04599] On Calibration of Modern Neural Networksarxiv.org
- Confidence Regulation Neurons in Language Modelsarxiv.org
- A Recipe for Training Neural Networkskarpathy.github.io
- Bayesian Neural Networkscs.toronto.edu
- A Recipe for Training Neural Networkskarpathy.github.io
- guo17a.pdfproceedings.mlr.press
- nn-notes.pdfboris-hanin.github.io
- Deep Anomaly Detection with Outlier Exposurearxiv.org
- Dealing with Overconfidence in Neural Networks: Bayesian Approach – Jonathan Ramkissoonjramkiss.github.io
- Feature Visualizationdistill.pub
- Understanding deep learning requires rethinking generalizationarxiv.org