Explaining How Deep Neural Networks Forget by Deep Visualization
By GIANG NGUYEN, Shuan Chen, Tae Joon Jun, Daeyoung Kim. 2020
10 citations recorded by the source corpus.
Explaining the behaviors of deep neural networks, usually considered as black boxes, is critical especially when they are now being adopted over diverse aspects of human life. Taking the advantages of interpretable machine learning (interpretable ML), this paper proposes a novel tool called Catastrophic Forgetting Dissector (or CFD) to explain catastrophic forgetting in continual learning settings. We also introduce a new method called Critical Freezing based on the observations of our tool. Experiments on ResNet articulate how catastrophic forgetting happens, particularly showing which components of this famous network are forgetting. Our new continual learning algorithm defeats various recent techniques by a significant margin, proving the capability of the investigation. Critical freezing not only attacks catastrophic forgetting but also exposes explainability.
Subfields: Artificial Intelligence
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Thang Van Doan
- Pierre Alquier
- Mehdi Abbana Bennani
- Bogdan Mazoure
- Guillaume Rabusseau
- Olivier Catoni
- Matthieu Lerasle
- Roberto Imbuzeiro Oliveira
Citations in the corpus
- A Theoretical Analysis of Catastrophic Forgetting through the NTK Overlap Matrix (2020, background): “Previous work either investigated this phenomenon empirically at different granularity levels (task level [Nguyen et al., 2019], neural network representations level [Ramasesh et al., 2020] ), or proposed a quantitative metric [Farquhar and Gal, 2018, Kemker et al., 2017, Nguyen et al., 2020].”