Research map / Architectures and efficiency / RNNs and normalization
Piecewise linear activations substantially shape the loss surfaces of neural networks
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.
Closest papers by meaning
- Small nonlinearities in activation functions create bad local minima in neural networks (ICLR 2019 · similarity 0.92)
- The Loss Surface of Deep and Wide Neural Networks (ICML 2017 · similarity 0.90)
- Pure and Spurious Critical Points: a Geometric Study of Linear Networks (ICLR 2020 · similarity 0.90)
- Critical Points of Linear Neural Networks: Analytical Forms and Landscape Properties (ICLR 2018 · similarity 0.90)
- Spurious Valleys and Clustering Behavior of Neural Networks (ICML 2023 · similarity 0.90)
- Flat Channels to Infinity in Neural Loss Landscapes (NeurIPS 2025 · similarity 0.87)
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.