Deep Learning
Neural architectures that learn hierarchical representations from large datasets.
Deep learning models learn layered representations directly from high-dimensional data like images, text, and audio. The families below dominate modern AI, from Transformers in language to CNNs in vision and GNNs over relational structures.
- Use Transformers for text, code, documents, multimodal AI, and modern recommendation/search pipelines.
- Use CNNs for classic image tasks and GNNs when relationships between entities matter.
| # | Algorithm | Best for | Common fields |
|---|---|---|---|
| 1 | Transformers | Language, vision-language, sequence modeling |
|
| 2 | Convolutional Neural Networks | Images, spatial data |
|
| 3 | Recurrent Neural Networks / LSTM / GRU | Sequential data, older NLP/time-series systems |
|
| 4 | Autoencoders | Compression, denoising, anomaly detection |
|
| 5 | Diffusion Models | Generative images/audio/video |
|
| 6 | Graph Neural Networks | Graph-structured data |
|
| 7 | Siamese / Contrastive Networks | Similarity learning |
|
| 8 | Neural Collaborative Filtering | Recommender systems |
|