Research map / Architectures and efficiency / RNNs and normalization
Brains on Beats
Umut Güçlü, Jordy Thielen, Michael Hanke, Marcel van Gerven
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 both time and frequency streams (DNN-TF) instead of time only (ablation) | DNN music tagger · MagnaTagATune | mean AUC: 0.8852 -> 0.8939 | Improved |
| use frequency-domain input instead of time-domain (ablation) | DNN music tagger · MagnaTagATune | mean AUC: 0.8852 -> 0.8905 | Improved |
| ensemble DNN-T and DNN-F predictions | DNN taggers · MagnaTagATune | mean AUC: 0.8939 -> 0.8982 | Improved |
| ensemble all three DNN models | DNN taggers · MagnaTagATune | mean AUC: 0.8982 -> 0.9007 | Improved |
| replace task-optimized DNN-TF with random-weight DNN (ablation) | DNN-TF · STG RSA | representational similarity (delta r): 0.21 | Hurt |
| replace DNN-TF with mel-frequency spectrum features (ablation) | DNN-TF · STG RSA | representational similarity (delta r): 0.42 | Hurt |
| replace DNN-TF with MFCC features (ablation) | DNN-TF · STG RSA | representational similarity (delta r): 0.21 | Hurt |
| replace DNN-TF with low-quefrency mel spectrum (ablation) | DNN-TF · STG RSA | representational similarity (delta r): 0.44 | Hurt |
| replace DNN-TF with high-quefrency mel spectrum (ablation) | DNN-TF · STG RSA | representational similarity (delta r): 0.34 | Hurt |
| random weights instead of trained weights in searchlight (ablation) | DNN-TF · STG layer gradient | layer-position correlation: 0.7255 -> -0.2175 | Hurt |
| tighten significance threshold from 0.05 to 0.01 in searchlight | DNN-TF · STG voxels | surviving voxels (%) / gradient r: 85.53% -> 75.32%; r 0.7255 -> 0.7332 | No clear effect |
| go from shallow Layer 1 to deep Layer 8 | DNN-TF · STG ROI RSA | Spearman r: 0.6811 -> 0.4429 | Hurt |
Closest papers by meaning
- AutoSchA: Automatic Hierarchical Music Representations via Multi-Relational Node Isolation (AAAI 2026 · similarity 0.82)
- Modeling Temporal Tonal Relations in Polyphonic Music Through Deep Networks With a Novel Image-Based Representation (AAAI 2018 · similarity 0.81)
- PerformanceNet: Score-to-Audio Music Generation with Multi-Band Convolutional Residual Network (AAAI 2019 · similarity 0.81)
- Deep Learning for Style Transfer and Experimentation with Audio Effects and Music Creation (AAAI 2024 · similarity 0.80)
- Neural decoding from stereotactic EEG: accounting for electrode variability across subjects (NeurIPS 2024 · similarity 0.80)
- Representing Sounds as Neural Amplitude Fields: A Benchmark of Coordinate-MLPs and a Fourier Kolmogorov-Arnold Framework (AAAI 2025 · similarity 0.79)
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.
