Research map / Architectures and efficiency / RNNs and normalization
Deep Reservoir Computing Meets 5G MIMO-OFDM Systems in Symbol Detection
Zhou Zhou, Lingjia Liu, Vikram Chandrasekhar, Jianzhong Zhang, Yang Yi
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 |
|---|---|---|---|
| stack RCs sequentially into deep RC (L=3) instead of a shallow RC (ablation) | RC-based MIMO-OFDM receiver · nonlinear PA, 16QAM, WINNER II channel | BER | Improved |
| use finer delay search (50 values) for the shallow time-domain RC instead of 5 (ablation) | shallow time-domain RC · training objective, Eb/N0 15 dB | training objective value | No clear effect |
| add extra RC layers on top of a shallow time-domain RC (ablation) | time-domain RC · training objective | objective value | Improved |
| add a time-frequency output layer (time, FFT, frequency) to the RC readout (ablation) | RC receiver · training objective | fitting error convergence | Improved |
| use RC-based receivers instead of LMMSE and sphere decoding in the linear PA region | MIMO-OFDM symbol detection · linear PA region, low Eb/N0 | BER | Improved |
| use deep RC at low input back-off (IBO below 5 dB) | RC receiver · PA nonlinear region | BER | Improved |
| increase number of stacked RC layers (ablation) | deep RC · test BER | generalization error | Mixed |
Closest papers by meaning
- Universality of Real Minimal Complexity Reservoir (AAAI 2025 · similarity 0.80)
- Exploiting Symmetric Temporally Sparse BPTT for Efficient RNN Training (AAAI 2024 · similarity 0.79)
- Accelerating Linear Recurrent Neural Networks for the Edge with Unstructured Sparsity (ICML 2025 · similarity 0.79)
- Model-Driven Deep Neural Network for Enhanced AoA Estimation Using 5G gNB (AAAI 2024 · similarity 0.79)
- Frequency Domain Reservoir Computing (NeurIPS 2026 · similarity 0.79)
- ZNO: Stable Rational Neural Operators in the Z-Domain for Discrete-Time Dynamics (NeurIPS 2026 · similarity 0.78)
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.
