Research map / Optimization / Implicit bias and generalization
Complex-valued Neurons Can Learn More but Slower than Real-valued Neurons via Gradient Descent
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 |
|---|---|---|---|
| use a complex-valued neuron instead of a real-valued neuron to learn a complex-valued target | single-neuron learner trained by gradient descent · complex-valued target neuron | learnability: Cannot Learn -> O(t−1) | Helped |
| use a complex-valued neuron instead of a real-valued neuron to learn a real-valued target | single-neuron learner trained by gradient descent · real-valued target neuron | convergence rate: O(e−ct) -> Θ(t−3) | Hurt |
Closest papers by meaning
- Optimal approximation using complex-valued neural networks (NeurIPS 2023 · similarity 0.86)
- Real-Valued Backpropagation is Unsuitable for Complex-Valued Neural Networks (NeurIPS 2022 · similarity 0.86)
- Learning a Single Neuron with Bias Using Gradient Descent (NeurIPS 2021 · similarity 0.85)
- On the Feasibility of Single-Pass Full-Capacity Learning in Linear Threshold Neurons with Binary Input Vectors (ICML 2024 · similarity 0.82)
- Transformers Implement Functional Gradient Descent to Learn Non-Linear Functions In Context (ICML 2024 · similarity 0.82)
- Complexity of Neural Network Training and ETR: Extensions with Effectively Continuous Functions (AAAI 2024 · similarity 0.81)
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.