✳flâneur — a map of the web's best reading
Loss Landscape | A.I deep learning explorations of morphology & dynamics
losslandscape.com · 2,925 words · saved by 1 readers
Explore the morphology and dynamics of deep learning optimization processes and gradient descent with the A.I Loss Landscape project.
Loss Exploring the Landscape Deep learning Explorers MOVING LANDS STILL LANDS METHOD Latest update: January 21, 2026 RosettaMind Refresh your mind by challenging it. Your collective memory garden powered by science and AI Explore Human GPT Quick trailer of the pioneering “Human GPT” performance that I recently designed and directed for the European AI Congress Watch Movie Launch: Hamelin 77 , our movie production that pioneered the use of Gen AI techniques in cinema launches in Amazon Prime Video (Europe/UK now and USA from September) Watch | Trailer NEW paper: SplInterp: Improving
Explore this link on the map →saved by
related reading
- LLM Visualizationbbycroft.net
- Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs | Pavel's Blogizmailovpavel.github.io
- The Little Book of Deep Learningfleuret.org
- Feature Visualizationdistill.pub
- GitHub - google-research/tuning_playbook: A playbook for systematically maximizing the performance of deep learning models. · GitHubgithub.com
- Thoughts on loss landscapes and why deep learning worksberen.io
- Thoughts on Loss Landscapes and why Deep Learning works — LessWronglesswrong.com
- Neuronpedianeuronpedia.org
- GitHub - jacobhilton/deep_learning_curriculum: Language model alignment-focused deep learning curriculum · GitHubgithub.com
- GenAI Handbookgenai-handbook.github.io
- Jacobian Lens – Qwen3.6-27B ｜ Neuronpedianeuronpedia.org
- How to visualize training dynamics in neural networks | ICLR Blogposts 2025iclr-blogposts.github.io