Research map / Architectures and efficiency / Spiking networks
Increasing Liquid State Machine Performance with Edge-of-Chaos Dynamics Organized by Astrocyte-modulated Plasticity
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| add astrocyte-modulated STDP to the LSM liquid | LSM 1000 neurons · MNIST | top accuracy: 95.44% -> 96.15% | Helped |
| add astrocyte-modulated STDP to the LSM liquid | LSM 1000 neurons · N-MNIST | top accuracy: 95.35% -> 96.13% | Helped |
| add astrocyte modulation to plain STDP (ablation) | LSM+STDP · MNIST | top accuracy: 90.52% -> 96.15% | Helped |
| add astrocyte modulation to plain STDP (ablation) | LSM+STDP · N-MNIST | top accuracy: 87.71% -> 96.13% | Helped |
| replace hand-tuned AP-STDP with astrocyte-modulated STDP | LSM+STDP · MNIST | top accuracy: 95.62% -> 96.15% | Helped |
| replace hand-tuned AP-STDP with astrocyte-modulated STDP | LSM+STDP · N-MNIST | top accuracy: 95.43% -> 96.13% | Helped |
| scale liquid from 1000 to 8000 neurons (ablation) | NALSM · MNIST | top accuracy: 96.15% -> 97.61% | Helped |
| scale liquid from 1000 to 8000 neurons (ablation) | NALSM · N-MNIST | top accuracy: 96.13% -> 97.51% | Helped |
| scale liquid from 1000 to 8000 neurons (ablation) | NALSM · Fashion-MNIST | top accuracy: 83.54% -> 85.84% | Helped |
| reduce neuron-astrocyte connection density to 10% (ablation) | NALSM · MNIST | mean accuracy: -0.36% | No clear effect |
| reduce neuron-astrocyte connection density to 10% (ablation) | NALSM · N-MNIST | mean accuracy: -0.14% | No clear effect |
Closest papers by meaning
- The Expressive Leaky Memory Neuron: an Efficient and Expressive Phenomenological Neuron Model Can Solve Long-Horizon Tasks. (ICLR 2024 · similarity 0.86)
- Learning the Plasticity: Plasticity-Driven Learning Framework in Spiking Neural Networks (NeurIPS 2025 · similarity 0.86)
- MA-Net: Rethinking Neural Unit in the Light of Astrocytes (AAAI 2024 · similarity 0.86)
- Neuronal Self-Adaptation Enhances Capacity and Robustness of Representation in Spiking Neural Networks (NeurIPS 2026 · similarity 0.85)
- The Dormant Spiking Neuron: A State-Driven Mechanism for Efficient Spiking Neural Networks (NeurIPS 2026 · similarity 0.85)
- SpikingSSMs: Learning Long Sequences with Sparse and Parallel Spiking State Space Models (AAAI 2025 · 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.