Research map / Continual learning / Online and replay-based
Gated Linear Networks
Joel Veness, Tor Lattimore, David Budden, Avishkar Bhoopchand, Christopher Mattern, Agnieszka Grabska-Barwinska, Eren Sezener, Jianan Wang, Peter Toth, Simon Schmitt, Marcus Hutter
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use halfspace-gated GLNs with local learning instead of an MLP with dropout or single-pass EWC | Permuted MNIST continual learning · Permuted MNIST | accuracy | Mixed |
| Increase the number of neurons and context dimension (ablation) | GLN · MNIST with shuffled labels and uniform-noise dataset | training-data memorization | Improved |
Closest papers by meaning
- Flat Channels to Infinity in Neural Loss Landscapes (NeurIPS 2025 · similarity 0.84)
- Implicit bias of SGD in $L_2$-regularized linear DNNs: One-way jumps from high to low rank (ICLR 2024 · similarity 0.84)
- On Vanishing Gradients, Over-Smoothing, and Over-Squashing in GNNs: Bridging Recurrent and Graph Learning (NeurIPS 2025 · similarity 0.84)
- Masked Gated Linear Unit (NeurIPS 2025 · similarity 0.84)
- On the Feasibility of Single-Pass Full-Capacity Learning in Linear Threshold Neurons with Binary Input Vectors (ICML 2024 · similarity 0.83)
- Rethinking Neural Nonlinearity as Gating (NeurIPS 2026 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
