Fetching the paper…
Reading the bibliography…
Neural networks have been criticised for their inability to perform continual learning due to catastrophic forgetting and rapid unlearning of a past concept when a new concept is introduced.
Universal approximations of permutation invariant/equivariant functions by deep neural networks
A. Sannai, Y. Takai, and M. Cordonnier · 1903
Earlier work this paper cites.
On the representation of continuous functions of many variables by superposition of continuous functions of one variable and addition
A. N. Kolmogorov · 1957
Earlier work this paper cites.
On the approximate realization of continuous mappings by neural networks
K.-I. Funahashi · 1989
Earlier work this paper cites.
Catastrophic interference in connectionist networks: The sequential learning problem
M. McCloskey and N. J. Cohen · 1989
Earlier work this paper cites.
Distributed representations
G. E. Hinton, J. L. McClelland, and D. E. Rumelhart · 1990
Earlier work this paper cites.
Multi-layer perceptrons with b-spline receptive field functions
S. H. Lane, M. Flax, D. Handelman, and J. Gelfand · 1991
Earlier work this paper cites.
Defeating the runge phenomenon for equispaced polynomial interpolation via tikhonov regularization
J. P. Boyd · 1992
Earlier work this paper cites.
Catastrophic interference is eliminated in pretrained networks
K. McRae and P. A. Hetherington · 1993
Earlier work this paper cites.
Catastrophic forgetting, rehearsal and pseudorehearsal
A. Robins · 1995
Earlier work this paper cites.
Universal approximation using feedforward neural networks: A survey of some existing methods, and some new results
F. Scarselli and A. C. Tsoi · 1998
Earlier work this paper cites.
Kolmogorov’s spline network
B. Igelnik and N. Parikh · 2003
Earlier work this paper cites.
The runge phenomenon and spatially variable shape parameters in rbf interpolation
B. Fornberg and J. Zuev · 2007
Cited alongside, same era.
The kolmogorov-arnold representation theorem revisited, 2020
J. Schmidt-Hieber · 2007
Cited alongside, same era.
On a constructive proof of kolmogorov’s superposition theorem
J. Braun and M. Griebel · 2009
Cited alongside, same era.
An overview of hierarchical temporal memory: A new neocortex algorithm
X. Chen, W. Wang, and W. Li · 2012
Cited alongside, same era.
Pseudo-recurrent connectionist networks: An approach to the ’sensitivity-stability’ dilemma
R. M. French · 2015
Cited alongside, same era.
Deep residual learning for image recognition
K. He, X. Zhang, S. Ren, and J. Sun · 2016
Approximation capability of two hidden layer feedforward neural networks with fixed weights
N. J. Guliyev and V. E. Ismailov · 2018
Later among the works it cites.
Mixup as locally linear out-of-manifold regularization, 2018
H. Guo, Y. Mao, and R. Zhang · 2018
Later among the works it cites.
Universal language model fine-tuning for text classification
J. Howard and S. Ruder · 2018
Later among the works it cites.
Manifold mixup: Better representations by interpolating hidden states, 2018
V. Verma, A. Lamb, C. Beckham, A. Najafi, I. Mitliagkas, A. Courville, D. Lopez-Paz, and Y. Bengio · 2018
Later among the works it cites.
Polynomial interpolation via mapped bases without resampling
S. De Marchi, F. Marchetti, E. Perracchione, and D. Poggiali · 2019
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Cited alongside, same era.
B-splines in machine learning
A. S. Douzette · 2017
Cited alongside, same era.
Overcoming catastrophic forgetting in neural networks
J. Kirkpatrick, R. Pascanu, N. Rabinowitz, J. Veness, G. Desjardins, A. A. Rusu, K. Milan, J. Quan, T. Ramalho, A. Grabska-Barwinska, D. Hassabis, C. Clopath, D. Kumaran, and R. Hadsell · 2017
Cited alongside, same era.
Learning activation functions from data using cubic spline interpolation
S. Scardapane, M. Scarpiniti, D. Comminiello, and A. Uncini · 2017
Cited alongside, same era.
Continual learning with deep generative replay
H. Shin, J. K. Lee, J. Kim, and J. Kim · 2017
Cited alongside, same era.
mixup: Beyond empirical risk minimization, 2017
H. Zhang, M. Cisse, Y. N. Dauphin, and D. Lopez-Paz · 2017
Cited alongside, same era.
Later among the works it cites.
A study on catastrophic forgetting in deep lstm networks
M. Schak and A. Gepperth · 2019
Later among the works it cites.
P. Kaushik, A. Gain, A. Kortylewski, and A. Yuille · 2021
Later among the works it cites.
A scalable continuous unbounded optimisation benchmark suite from neural network regression, 2021
K. M. Malan and C. W. Cleghorn · 2021
Later among the works it cites.
The kolmogorov–arnold representation theorem revisited
J. Schmidt-Hieber · 2021
Later among the works it cites.
Neural network approximation: Three hidden layers are enough
Z. Shen, H. Yang, and S. Zhang · 2021
Later among the works it cites.