2018

Don't forget, there is more than forgetting: new metrics for Continual Learning

Díaz-Rodríguez, Natalia, Lomonaco, Vincenzo, Filliat, David et al.

Understand

Continual learning consists of algorithms that learn from a stream of data/tasks continuously and adaptively thought time, enabling the incremental development of ever more complex knowledge and skills.

  • The lack of consensus in evaluating continual learning algorithms and the almost exclusive focus on forgetting motivate us to propose a more comprehensive set of implementation independent metrics accounting for several factors we believe have practical implications worth considering in the deployment of real AI systems that learn continually: accuracy or performance over time, backward and forward knowledge transfer, memory overhead as well as computational efficiency.
  • Drawing inspiration from the standard Multi-Attribute Value Theory (MAVT) we further propose to fuse these metrics into a single score for ranking purposes and we evaluate our proposal with five continual learning strategies on the iCIFAR-100 continual learning benchmark.

Built on

  • Catastrophic interference in connectionist networks: The sequential learning problem

    McCloskey, M. and Cohen, N. J. (1989) · 1989

    Earlier work this paper cites.

  • Decision with multiple objectives, preferences and value tradeoffs

    Keeney, R. and Raiffa, H. (1993) · 1993

    Earlier work this paper cites.

  • Catastrophic forgetting in connectionist networks

    French, R. M. (1999) · 1999

    Earlier work this paper cites.

  • Learning Multiple Layers of Features from Tiny Images

    Krizhevsky, A. (2009) · 2009

    Earlier work this paper cites.

  • Multi-criteria decision analysis: methods and software

    Ishizaka, A. and Nemery, P. (2013) · 2013

    Earlier work this paper cites.

Similar

  • Overcoming catastrophic forgetting in neural networks

    Kirkpatrick, J., Pascanu, R., Rabinowitz, N., Veness, J., Desjardins, G., Rusu, A. A., Milan, K., Quan, J., Ramalho, T., Grabska-Barwinska, A., Hassabis, D., Clopath, C., Kumaran, D., and Hadsell, R. (2016) · 2016

    Cited alongside, same era.

  • Learning without Forgetting

    Li, Z. and Hoiem, D. (2016) · 2016

    Cited alongside, same era.

  • Core50: a new dataset and benchmark for continuous object recognition

    Lomonaco, V. and Maltoni, D. (2017) · 2017

    Cited alongside, same era.

  • Gradient Episodic Memory for Continual Learning

    Lopez-Paz, D. and Ranzato, M. (2017) · 2017

    Cited alongside, same era.

  • Continual learning through synaptic intelligence

    Zenke, F., Poole, B., and Ganguli, S. (2017) · 2017

    Cited alongside, same era.

Then

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…