Deep Learning in Banking

List of Algorithms

1. 2.1 Image Data: Data loading and preprocessing.
2. 2.2 Image Data: Create data loaders.
3. 2.3 Image Data: Define simple CNN regressor.
4. 2.4 Image Data: Train simple model.
5. 2.5 Image Data: Evaluate simple model.
6. 2.6 Image Data: Grad-CAM for model explainability.
7. 2.7 Image Data: ResNet-50 model.
8. 2.8 Image Data: Train ResNet-50.
9. 2.9 Image Data: Evaluate ResNet-50.
10. 3.1 Time Series: Data loading.
11. 3.2 Time Series: Data preprocessing.
12. 3.3 Time Series: Create data loaders.
13. 3.4 Time Series: Create recurrent model.
14. 3.5 Time Series: Load static data.
15. 3.6 Time Series: Define hybrid model.
16. 3.7 Time Series: Training loop.
17. 3.8 Time Series: Validation loop.
18. 3.9 Time Series: Running the models—Hybrid GRU model.
19. 4.1 Text Data: Data loading.
20. 4.2 Text Data: Preprocessing.
21. 4.3 Text Data: Fine tuning a BERT model.
22. 4.4 Text Data: Inference on new data.
23. 5.1 Network Data: Data loading and network creation.
24. 5.2 Network Data: Define GNN models.
25. 5.3 Network Data: Training and validation loop.
26. 5.4 Network Data: Model evaluation.
27. 6.1 LLM: Initial setup.
28. 6.2 LLM: Zero-shot prompting.
29. 6.3 LLM: Detailed LLM prompt engineering and fine-tuning for credit score explainability.
30. 6.4 LLM: Fine-tuning.
31. 6.5 LLM: Testing on new cases.
32. 7.1 Multimodal Learning: Load and process the data sources.
33. 7.2 Multimodal Learning: Pre-process all different channels.
34. 7.3 Multimodal Learning: Integrate features and create datasets.
35. 7.4 Multimodal Learning: Define the models.
36. 7.5 Multimodal Learning: Model training loop. ...