Research map / Continual learning / Online and replay-based
BayesPCN: A Continually Learnable Predictive Coding Associative Memory
Jinsoo Yoo, Frank Wood
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 BayesPCN instead of online GPCN | BayesPCN · hetero-associative Mask CIFAR10, 1024 images | MSE: 0.0791 -> 0.0019 | Improved |
| use BayesPCN instead of online GPCN | BayesPCN · hetero-associative Dropout CIFAR10, 1024 images | MSE: 0.0073 -> 0.0001 | Improved |
| use BayesPCN instead of online GPCN at 1024 images | BayesPCN · White Noise CIFAR10 auto-associative | MSE: 0.0210 -> 0.0337 | Hurt |
| use BayesPCN instead of online GPCN at 1024 images | BayesPCN · White Noise Tiny ImageNet auto-associative | MSE: 0.0181 -> 0.6606 | Hurt |
| use BayesPCN instead of online GPCN at 128 images | BayesPCN · White Noise CIFAR10 auto-associative | MSE: 0.0103 -> 0.0017 | Improved |
| add forget operation to BayesPCN at 1024 images (ablation) | BayesPCN · White Noise CIFAR10 | MSE: 0.0337 -> 0.0188 | Improved |
| add forget operation to BayesPCN at 1024 images (ablation) | BayesPCN · White Noise Tiny ImageNet | MSE: 0.6606 -> 0.0176 | Improved |
| add forget operation to BayesPCN at 1024 images (ablation) | BayesPCN · Mask CIFAR10 | MSE: 0.0019 -> 0.0465 | Hurt |
| add forget operation to BayesPCN at 1024 images (ablation) | BayesPCN · Mask Tiny ImageNet | MSE: 0.0000 -> 0.0235 | Hurt |
| increase forget strength beta (0 to 0.02) (ablation) | BayesPCN · CIFAR10, 1024 images | recall MSE on recent batches | Improved |
| use BayesPCN instead of MHN under high query noise (dropout 75%) | BayesPCN · Dropout CIFAR10, 128 images | MSE: 0.3840 -> 0.0000 | Improved |
| use BayesPCN instead of MHN under high noise white noise | BayesPCN · White Noise CIFAR10, 128 images | MSE: 0.0052 -> 0.0755 | Hurt |
Closest papers by meaning
- Memory Aware Synapses: Learning what (not) to forget (ECCV 2018 · similarity 0.87)
- Learning to Remember More with Less Memorization (ICLR 2019 · similarity 0.86)
- Predictive Attractor Models (NeurIPS 2024 · similarity 0.86)
- Factual recall in linear associative memories: sharp asymptotics and mechanistic insights (NeurIPS 2026 · similarity 0.85)
- Predicting the Susceptibility of Examples to Catastrophic Forgetting (ICML 2025 · similarity 0.85)
- Semantically-correlated memories in a dense associative model (ICML 2024 · similarity 0.85)
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.
