Indian Buffet Neural Networks for Continual Learning

By Samuel Kessler, Vu Nguyen, Stefan Zohren, Stephen J. Roberts. 2019

6 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Tom Véniat
2. Ludovic Denoyer
3. Abhishek Kumar
4. Piyush Rai
5. Marc'Aurelio Ranzato
6. Yu Zhang
7. Yoshua Bengio
8. Qiang Yang

Citations in the corpus

• Efficient Continual Learning with Modular Networks and Task-Driven Priors (2020, background): “Non-modular approaches, like those relying on individual neuron gating (Adel et al., 2020; Serr`a et al., 2018; Kessler et al., 2019), lack such runtime efficiency which limits their applicability to long streams.”
• Bayesian Structure Adaptation for Continual Learning (2019, background): “In another recent work (simultaneous development with our work), (Kessler et al., 2019) did a pre-liminary investigation on using IBP for continual learning.”
• A Continual Learning Framework for Uncertainty-Aware Interactive Image Segmentation (2021, methodology): “The proposed framework is closely related to the works of variational continual learning (Nguyen et al. 2018; Kessler et al. 2019), which leverages Bayesian neural networks to retain a distribution over model parameters, and IBP priors to automatically determine the complexity of network.”