Pith. sign in

REVIEW 2 cited by

Plastic Learning with Deep Fourier Features

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2410.20634 v1 pith:AFFW6FX7 submitted 2024-10-27 cs.LG

classification cs.LG
keywords deeplearningfeaturesfouriernetworkscontinualresultslinear
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Deep neural networks can struggle to learn continually in the face of non-stationarity. This phenomenon is known as loss of plasticity. In this paper, we identify underlying principles that lead to plastic algorithms. In particular, we provide theoretical results showing that linear function approximation, as well as a special case of deep linear networks, do not suffer from loss of plasticity. We then propose deep Fourier features, which are the concatenation of a sine and cosine in every layer, and we show that this combination provides a dynamic balance between the trainability obtained through linearity and the effectiveness obtained through the nonlinearity of neural networks. Deep networks composed entirely of deep Fourier features are highly trainable and sustain their trainability over the course of learning. Our empirical results show that continual learning performance can be drastically improved by replacing ReLU activations with deep Fourier features. These results hold for different continual learning scenarios (e.g., label noise, class incremental learning, pixel permutations) on all major supervised learning datasets used for continual learning research, such as CIFAR10, CIFAR100, and tiny-ImageNet.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. PreScience: A Dataset and Benchmark for Scientific Forecasting

    cs.AI 2026-02 conditional novelty 6.0 of 10

    A new benchmark tests whether AI can forecast future scientific papers; frontier LLMs score ~5.6/10 on matching real abstracts, and simulated corpora are measurably less diverse and novel than human science.

  2. Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss

    cs.LG 2025-02 conditional novelty 5.0 of 10

    AID, a stochastic activation applying different dropout rates to positive and negative preactivations, mitigates plasticity loss and improves continual learning, reinforcement learning, and standard supervised learnin...

Pith tools