CHARLA IFLYSIB VIRTUAL Miércoles 21/08 · Santiago Acevedo · «Detección no supervisada de correlaciones semánticas en redes neuronales artificiales»

Título: Detección no supervisada de correlaciones semánticas en redes neuronales artificiales

Expositor: Santiago Acevedo – International School for Advanced Studies (SISSA), Trieste, Italia

Fecha: Miércoles 21/08/2024 – 10:30 hs. ¡DÍA EXTRAORDINARIO!

Resumen:

In real-world data, information is stored in extremely large feature vectors. These features are often correlated due to complex interactions involving multiple features simultaneously. These correlations qualitatively correspond to semantic roles and are naturally recognized by both the human brain and artificial neural networks. This recognition enables, for instance, the prediction of missing parts of an image or text based on their context. We present a method to detect such correlations in high-dimensional data, represented as binary numbers. We estimate the binary intrinsic dimension of a dataset, which quantifies the minimum number of independent coordinates needed to describe the data, and is therefore a proxy of semantic complexity. The proposed algorithm is largely insensitive to the so-called curse of dimensionality, and can therefore be used in big data analysis. We test this approach identifying phase transitions in model magnetic systems and we then apply it to the detection of semantic correlations of images and text inside deep neural networks.

Solicitar link de acceso a charlas.iflysib@gmail.com