Research map / Architectures and efficiency / RNNs and normalization
CORNN: Convex optimization of recurrent neural networks for rapid inference of neural dynamics
Fatih Dinc, Adam Shai, Mark Schnitzer, Hidenori Tanaka
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 |
|---|---|---|---|
| train with teacher forcing in BPTT (ablation) | BPTT · Chaotic RNN reproduction (Fig. S1) | convergence speed | Improved |
| use cross-entropy loss instead of L2 loss (ablation) | BPTT · Chaotic RNN reproduction (Fig. S1) | reproduction accuracy | Improved |
| replace FORCE with CORNN | dRNN training · Random chaotic RNN, 5000 neurons | training time: 4 orders of magnitude | Improved |
| add fixed-point initialization to CORNN (ablation) | CORNN · Chaotic RNN reproduction (Fig. S6C) | convergence speed and accuracy | Improved |
| fixed-point initialization added to other algorithms | other solvers · Chaotic RNN reproduction | stability | Improved |
| run CORNN on GPU instead of CPU | CORNN · Chaotic RNN reproduction (Fig. S5) | efficiency | Improved |
| subsample observed neurons to 10% and jitter time-scales | CORNN · Timed-response task | reproduction of neural dynamics | No clear effect |
| subsample observed neurons to 10% and jitter time-scales | CORNN · Timed-response task | sub-connectivity matrix reconstruction | Hurt |
| increase number of training trials | CORNN · Large generator networks (Fig. S8) | reproduction accuracy | Improved |
Closest papers by meaning
- Sign Gradient Descent-based Neuronal Dynamics: ANN-to-SNN Conversion Beyond ReLU Network (ICML 2024 · similarity 0.89)
- Second-order forward-mode optimization of recurrent neural networks for neuroscience (NeurIPS 2024 · similarity 0.88)
- Inference of Neural Dynamics Using Switching Recurrent Neural Networks (NeurIPS 2024 · similarity 0.88)
- Partial observation can induce mechanistic mismatches in data-constrained models of neural dynamics (NeurIPS 2024 · similarity 0.88)
- Scaling Laws and Tradeoffs in Recurrent Networks of Expressive Neurons (NeurIPS 2026 · similarity 0.88)
- Recurrent neural network dynamical systems for biological vision (NeurIPS 2024 · similarity 0.88)
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.
