ALASSO extends Synaptic Intelligence with an asymmetric quadratic surrogate loss whose unobserved side is overestimated, and it reports near-upper-bound accuracy on permuted MNIST, split CIFAR, and split Tiny ImageNet.
Riemannian walk for incremen- tal learning: Understanding forgetting and intransigence
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation
ALASSO extends Synaptic Intelligence with an asymmetric quadratic surrogate loss whose unobserved side is overestimated, and it reports near-upper-bound accuracy on permuted MNIST, split CIFAR, and split Tiny ImageNet.