Deep Residual Learning for Image Recognition
Add the input back — the identity skip that made 152-layer nets trainable.
He et al. · CVPR 2016 · Foundations. Read the paper ↗
A free, interactive, animated visual explainer of Deep Residual Learning for Image Recognition — every exhibit computed from the real formulas, with verbatim quotes from the source.
Questions
- What is Deep Residual Learning for Image Recognition?
- Add the input back — the identity skip that made 152-layer nets trainable.
- Who published Deep Residual Learning for Image Recognition, and where?
- He et al. — CVPR 2016 (arXiv:1512.03385).
- Where can I find a visual explainer of Deep Residual Learning for Image Recognition?
- Right here — a free, interactive, animated walkthrough of the whole paper, with exhibits computed from the real formulas and verbatim quotes from the source.
Related explainers
- Attention Is All You Need
- GPT-3: Language Models are Few-Shot Learners
- Mixtral of Experts
- Training Compute-Optimal Large Language Models
- Mamba: Linear-Time Sequence Modeling with Selective State Spaces
- BERT: Pre-training of Deep Bidirectional Transformers
- Scaling Laws for Neural Language Models
- Adam: A Method for Stochastic Optimization