# Well-known references for ML and GeoSciML 
## Classical DL Architectures

### Computer Vision

**Historical paper**
- [Learning representations by back-propagating errors, 1986](https://doi.org/10.1038/323533a0) 
- [Gradient-based learning applied to document recognition](10.1109/5.726791)


**Convolutional neural network (CNNs):**
- [ImageNet Classification with Deep Convolutional Neural Networks](https://papers.nips.cc/paper/2012/hash/c399862d3b9d6b76c8436e924a68c45b-Abstract.html) — AlexNet (Krizhevsky et al., 2012)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://arxiv.org/abs/1409.1556) — VGG (Simonyan & Zisserman, 2014)
- [Deep Residual Learning for Image Recognition](https://arxiv.org/abs/1512.03385) — ResNet (He et al., 2015)
- [Rethinking the Inception Architecture for Computer Vision](https://arxiv.org/abs/1512.00567) — Inception (Szegedy et al., 2015)

**Derived CNNs:**
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://arxiv.org/abs/1505.04597) — Segmentation
- [You Only Look Once](https://arxiv.org/abs/1506.02640) — YOLO (Object Detection)
- [Mask R-CNN](https://arxiv.org/abs/1703.06870) — Instance Segmentation
- [ViT](https://doi.org/10.48550/arXiv.2010.11929) - Vision Transformers
- [ConvNeXt](A ConvNet for the 2020s)
- [EfficientNet](https://doi.org/10.48550/arXiv.1905.11946)


## Generative methods
**Autoencoders & VAE:**
- [Auto-Encoding Variational Bayes](https://doi.org/10.48550/arXiv.1312.6114)
- [An Introduction to Variational Autoencoders](https://arxiv.org/pdf/1906.02691)


**Generative Adversarial Networks:**
- [Generative Adversarial Networks](https://arxiv.org/abs/1406.2661) — GAN (Goodfellow et al., 2014)
- [Conditional Generative Adversarial Nets](https://arxiv.org/abs/1411.1784) — cGAN

**Diffusion Models:**
- [Diffusion Models: A Comprehensive Survey of Methods and Applications](https://arxiv.org/abs/2209.00796)
- [Denoising Diffusion Probabilistic Models](https://arxiv.org/abs/2006.11239) — DDPM (Ho et al., 2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://arxiv.org/abs/2112.10752) — Stable Diffusion

**Flow Matching**
- [Flow Matching for Generative Modeling](https://doi.org/10.48550/arXiv.2210.02747)
- [Flow Matching Guide and Code](https://arxiv.org/abs/2412.06264)
- [SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers](https://arxiv.org/abs/2401.08740)

## Datasets


## GeoSciML data challenges and benchmarks