Pesquisa

De onde vêm os próximos três anos deste trabalho.

O trabalho por trás dos sistemas: dissertações, projetos, os métodos que usaram e as perguntas que foram feitos para responder.

• Previsão da expressão génica (biologia molecular) a partir de imagens de patologia digital

  Gene-expression assays are slow, expensive and logistically painful. Whole-slide pathology images are fast and cheap. This thesis asks whether the second can stand in for the first — recovering molecular-biology signal directly from gigapixel pathology images, under a hard constraint on compute and latency. The approach combines graph neural networks, vision foundation models, large-language-model techniques adapted for this task, and statistical/probabilistic methods.

• Simulação da cognição visual humana e distinção entre perceção real e alucinação

  A year-long study using generative models — autoencoders and GANs — to model how the human brain constructs visual understanding, and to distinguish genuine perception from hallucination.