Actualizado:
Beyond a single train/test split: rigorous model evaluation, statistical uncertainty, pixel-to-feature explainability and faithfulness tests.
Actualizado:
A complete hands-on workflow from tabular rows to synthetic images and CNN, ViT, HyCNN and HyViT architectures.
Actualizado:
Learn how TINTOlib combines complementary unsupervised representations across RGB channels with mixMethod and how SSIM can be used to select a structurally stable number of clusters.
Actualizado:
Learn how gaussianMix, KDE and Factor Analysis transform tabular samples into grayscale synthetic images through membership probabilities, density estimates and latent-factor scores.
Actualizado:
Learn how k-means, k-medoids and aggloKNN convert relationships between tabular samples into grayscale synthetic images, including distance metrics, reference ordering and RBF smoothing.
Actualizado:
Learn how the new TINTOlib Clusters method converts distances, membership probabilities, density estimates and latent factors into synthetic images for vision-based deep learning.
Actualizado:
A practical and methodological comparison of TINTO, REFINED and IGTD for transforming tabular data into synthetic images and applying vision-based deep learning models.
Actualizado:
How TINTOlib transforms tabular data into synthetic images, which spatial encoding methods should be preferred, and how hybrid neural networks and explainable AI complete the modelling pipeline.
Actualizado:
Why deep learning still struggles with tabular data, and why synthetic image representations provide a promising bridge between structured data and computer vision architectures.
Actualizado:
An introduction to TINTOlib: why tabular data requires spatial encoding, how to generate synthetic images avoiding data leakage, and a complete end-to-end CNN pipeline in PyTorch.
Actualizado:
Technical introduction to TINTOlib, a Python framework for transforming tabular data into synthetic images and applying CNN-based deep learning architectures.