--- license: apache-2.0 library_name: numpy tags: - tabular-classification - tiny-model - edge-ai - no-gpu - numpy - real-time - ecg - eeg - seizure-detection - activity-recognition - medical-ai - biosignal - analytic-gradients datasets: - shayanfazeli/heartbeat - birdy654/eeg-brainwave-dataset-feeling-emotions - robikscube/eye-state-classification-eeg-dataset - harunshimanto/epileptic-seizure-recognition - uciml/human-activity-recognition-with-smartphones metrics: - accuracy - f1 - roc_auc model-index: - name: KestrelNet / GoshawkNet Benchmark Suite results: - task: type: tabular-classification name: ECG Arrhythmia Detection dataset: type: shayanfazeli/heartbeat name: MIT-BIH Arrhythmia metrics: - name: Accuracy type: accuracy value: 0.972 - name: Macro F1 type: f1 value: 0.853 - task: type: tabular-classification name: EEG Emotion Recognition dataset: type: birdy654/eeg-brainwave-dataset-feeling-emotions name: EEG Brainwave Emotions metrics: - name: Accuracy type: accuracy value: 0.991 - name: Macro F1 type: f1 value: 0.991 - task: type: tabular-classification name: EEG Eye State Detection dataset: type: robikscube/eye-state-classification-eeg-dataset name: EEG Eye State (UCI) metrics: - name: Accuracy type: accuracy value: 0.942 - name: AUC-ROC type: roc_auc value: 0.986 - task: type: tabular-classification name: Epileptic Seizure Detection dataset: type: harunshimanto/epileptic-seizure-recognition name: Bonn University EEG metrics: - name: Accuracy type: accuracy value: 0.971 - name: AUC-ROC type: roc_auc value: 0.988 - task: type: tabular-classification name: Human Activity Recognition dataset: type: uciml/human-activity-recognition-with-smartphones name: UCI HAR Smartphones metrics: - name: Accuracy type: accuracy value: 0.949 - name: Macro F1 type: f1 value: 0.949 pipeline_tag: tabular-classification --- # KestrelNet / GoshawkNet — Benchmark Suite **Here's what a tiny model can do.** Five public datasets. Five domains. All under 164K parameters. All CPU-only. All pure NumPy — no PyTorch, no TensorFlow, no GPU. Every result verified on Kaggle with live scoring. ## Results | Dataset | Domain | Task | Accuracy | F1 / AUC | Params | Size | Latency | |---|---|---|---|---|---|---|---| | [MIT-BIH Arrhythmia](https://kaggle.com/datasets/shayanfazeli/heartbeat) | Cardiology | 5-class ECG | **97.2%** | F1 0.853 | 12,756 | 50 KB | 56 μs | | [EEG Brainwave Emotions](https://kaggle.com/datasets/birdy654/eeg-brainwave-dataset-feeling-emotions) | Neuroscience | 3-class EEG | **99.1%** | F1 0.991 | 163,788 | 640 KB | 1.3 ms | | [EEG Eye State](https://kaggle.com/datasets/robikscube/eye-state-classification-eeg-dataset) | Neuroscience | Binary EEG | **94.2%** | AUC 0.986 | 1,576 | 6 KB | 17 μs | | [Epileptic Seizure](https://kaggle.com/datasets/harunshimanto/epileptic-seizure-recognition) | Neurology | Binary EEG | **97.1%** | AUC 0.988 | 12,072 | 47 KB | — | | [HAR Smartphones](https://kaggle.com/datasets/uciml/human-activity-recognition-with-smartphones) | Wearables | 6-class IMU | **94.9%** | F1 0.949 | 15,416 | 60 KB | 70 μs | Total model storage for all five: **803 KB**. For context, a single layer of BERT is 7 million parameters. Our five models combined have 205,608. ## How Small Is Small? | Dataset | Typical CNN/LSTM | Ours | How much smaller | |---|---|---|---| | ECG Heartbeat | 500K – 2M params | 12,756 | **40–160x** | | EEG Emotions | 1M+ params | 163,788 | **6x** | | EEG Eye State | 100K+ params | 1,576 | **63x** | | Seizure Detection | 200K+ params | 12,072 | **17x** | | HAR Smartphones | 200K – 1M params | 15,416 | **13–65x** | ## Two Model Families We ship two architectures, named after raptors — bird size matches model size, hunting style matches classification style. ### KestrelNet (Standard FC) The kestrel is the smallest falcon. It hovers perfectly still, then strikes with precision. KestrelNet is a standard fully-connected network with ReLU activations. Minimal parameters, maximum accuracy. ``` Input → Dense(hidden₁, ReLU) → Dense(hidden₂, ReLU) → Dense(classes, Softmax) ``` ### GoshawkNet (Multivector Products) The goshawk is a larger raptor that hunts in complex terrain, reading patterns others miss. GoshawkNet replaces standard dot products with multivector products, giving each neuron native access to rotations, reflections, and scaling in a single operation. More parameters, but captures geometric structure in the data that FC nets need many more layers to approximate. **Best model per dataset:** | Dataset | Best Model | Architecture | |---|---|---| | ECG Heartbeat | GoshawkNet Cl(0,2) | Quaternion, [16, 8] hidden | | EEG Emotions | GoshawkNet Cl(0,2) | Quaternion, [16, 8] hidden | | EEG Eye State | GoshawkNet Cl(0,2) | Quaternion, [16, 8] hidden | | Seizure Detection | GoshawkNet Cl(0,2) | Quaternion, [16, 8] hidden | | HAR Smartphones | GoshawkNet Cl(0,2) | Quaternion, [16, 8] hidden | Quaternion algebra (Cl(0,2), dimension 4) consistently wins across all five domains. ## Per-Dataset Details ### ECG Heartbeat — MIT-BIH Arrhythmia Database - **Samples**: 87,554 train / 21,892 test - **Features**: 187 time-series values per heartbeat - **Classes**: Normal (N), Supraventricular (S), Ventricular (V), Fusion (F), Unknown (Q) - **Best model**: GoshawkNet Cl(0,2) [16,8] — 97.2% accuracy, 12,756 params - **Kaggle notebook**: [samareddy94/gnaninet-ecg-benchmark](https://www.kaggle.com/code/samareddy94/gnaninet-ecg-benchmark) | Class | Accuracy | |---|---| | Normal (N) | 99.2% | | Supraventricular (S) | 64.6% | | Ventricular (V) | 90.9% | | Fusion (F) | 63.0% | | Unknown (Q) | 95.9% | ### EEG Brainwave Emotions - **Samples**: 2,132 (1,707 train / 425 test) - **Features**: 2,548 EEG features (channel means + FFT) - **Classes**: Negative, Neutral, Positive - **Best model**: GoshawkNet Cl(0,2) [16,8] — 99.1% accuracy, 163,788 params - **Kaggle notebook**: [samareddy94/99-eeg-emotion-detection-164k-params-no-gpu](https://www.kaggle.com/code/samareddy94/99-eeg-emotion-detection-164k-params-no-gpu) | Class | Accuracy | |---|---| | Negative | 99.3% | | Neutral | 100.0% | | Positive | 97.9% | ### EEG Eye State — UCI / Roesler - **Samples**: 14,980 (11,985 train / 2,995 test) - **Features**: 14 EEG channels (AF3, F7, F3, FC5, T7, P7, O1, O2, P8, T8, FC6, F4, F8, AF4) - **Classes**: Eyes Open, Eyes Closed - **Best model**: GoshawkNet Cl(0,2) [16,8] — 94.2% accuracy, 1,576 params - **Kaggle notebook**: [samareddy94/gnaninet-eeg-eyestate-benchmark](https://www.kaggle.com/code/samareddy94/gnaninet-eeg-eyestate-benchmark) The smallest model in the suite: **1,576 parameters, 6 KB**. Runs at 60,000 inferences/sec on CPU. ### Epileptic Seizure Recognition — Bonn University - **Samples**: 11,500 (9,200 train / 2,300 test) - **Features**: 178 EEG time-series values - **Classes**: Seizure vs Non-seizure (binary) - **Best model**: GoshawkNet Cl(0,2) [16,8] — 97.1% accuracy, AUC 0.988, 12,072 params AUC of 0.988 means the model correctly ranks seizure vs non-seizure 98.8% of the time — critical for clinical screening. ### HAR Smartphones — UCI Activity Recognition - **Samples**: 7,352 train / 2,947 test (official split) - **Features**: 228 triaxial accelerometer + gyroscope features - **Classes**: Walking, Walking Upstairs, Walking Downstairs, Sitting, Standing, Laying - **Best model**: GoshawkNet Cl(0,2) [16,8] — 95.7% local / 94.9% Kaggle live, 15,416 params - **Kaggle notebook**: [samareddy94/gnaninet-har-benchmark](https://www.kaggle.com/code/samareddy94/gnaninet-har-benchmark) | Class | Accuracy | |---|---| | Walking | 99.0% | | Walking Upstairs | 90.7% | | Walking Downstairs | 96.4% | | Sitting | 91.9% | | Standing | 95.7% | | Laying | 99.8% | ## Training Details All models trained with the same configuration: - **Optimizer**: Adam (lr=0.001, β₁=0.9, β₂=0.999) - **LR Schedule**: Warmup-cosine (10-epoch warmup) - **Early stopping**: Patience 30–40 on validation loss - **Batch size**: 64–128 - **L2 regularization**: λ = 1e-4 to 1e-5 - **Gradient clipping**: 5.0 - **Normalization**: Z-score, fit on training set only - **Backpropagation**: Analytic (hand-derived gradients, no autograd) Training is fast — all five models train in under 10 minutes total on a laptop CPU. ## Repository Structure ``` ├── ecg-heartbeat/ │ ├── weights.txt # GoshawkNet Cl(0,2) [16,8] — 97.2% accuracy │ └── results.json # Full benchmark comparison (4 models) ├── eeg-emotions/ │ ├── weights.txt # GoshawkNet Cl(0,2) [16,8] — 99.1% accuracy │ └── results.json ├── eye-state/ │ ├── weights.txt # GoshawkNet Cl(0,2) [16,8] — 94.2% accuracy │ └── results.json ├── seizure-prediction/ │ ├── weights.txt # GoshawkNet Cl(0,2) [16,8] — 97.1% accuracy │ └── results.json ├── har-smartphones/ │ ├── weights.txt # GoshawkNet Cl(0,2) [16,8] — 94.9% accuracy │ └── results.json └── inference.py # Self-contained inference loader (no dependencies beyond NumPy) ``` ## Quick Start ```python import numpy as np from inference import load_model # Load any model model = load_model("ecg-heartbeat") proba = model.predict_proba(np.random.randn(187)) print(proba) # [0.92, 0.01, 0.05, 0.01, 0.01] — 5-class probabilities ``` ## Intended Use - **Clinical screening**: Pre-filter for ECG/EEG analysis before specialist review - **Edge deployment**: Wearables, IoT sensors, embedded devices — no GPU, no cloud - **Ensemble first stage**: Fast, tiny model screens easy cases; complex model handles the rest - **Research baseline**: Reproducible benchmarks on public datasets with minimal compute - **Education**: Complete from-scratch neural network with analytic gradients ## Limitations - Models are trained on tabular/flattened features, not raw waveforms - Per-class accuracy varies — rare classes (ECG Fusion, ECG Supraventricular) have lower recall - No sequence modeling — each sample is classified independently - Medical models are NOT validated for clinical use — research benchmarks only ## Kaggle Verification All results except seizure prediction have been verified with live Kaggle notebook scoring: | Dataset | Kaggle Notebook | |---|---| | ECG Heartbeat | [samareddy94/gnaninet-ecg-benchmark](https://www.kaggle.com/code/samareddy94/gnaninet-ecg-benchmark) | | EEG Emotions | [samareddy94/99-eeg-emotion-detection-164k-params-no-gpu](https://www.kaggle.com/code/samareddy94/99-eeg-emotion-detection-164k-params-no-gpu) | | EEG Eye State | [samareddy94/gnaninet-eeg-eyestate-benchmark](https://www.kaggle.com/code/samareddy94/gnaninet-eeg-eyestate-benchmark) | | HAR Smartphones | [samareddy94/gnaninet-har-benchmark](https://www.kaggle.com/code/samareddy94/gnaninet-har-benchmark) | ## Citation ```bibtex @misc{kestrelnet-benchmarks-2026, title={KestrelNet/GoshawkNet: Tiny Neural Classifiers for Biosignal and Sensor Data}, author={Sama Reddy}, year={2026}, url={https://huggingface.co/reddysama/kestrelnet-benchmarks} } ``` ---

No PyTorch. No TensorFlow. No GPU. Just NumPy and math.
Fraud Classifier · Live Demo · Website