Classification

Assess distribution models with complementary measures of discrimination, classification, explanatory power and calibration. Interactive R exercises show why evaluation should reflect species’ ecological and geographic characteristics rather than relying on a single statistic. Participants validate models beyond their training areas, including spatial block cross-validation, and may work with their own observed and predicted values or supplied examples. Live sessions: 20 and 22 October, 10:00–14:00, Europe/Madrid (CEST, UTC+02:00); eight teaching hours. English-language live online course; F

…sequences complicate assembly and classification. Participants will compare reconstruction approaches, explore the

Unlike conventional deep neural networks, the human brain has a myriad of direct connections from subcortical nuclei to all cortical areas [1,2]. These enable fast information transfer and facilitate hierarchical compositionality but have not yet been explored in artificial systems [3]. In this work, we present the Shallow Hierarchical Artificial Neural Network (SHANN), a novel brain-inspired architecture with shallow connections from the input to all the hierarchical processing layers. Like conventional deep networks, SHANNs can achieve high levels of abstraction in more hierarchical layers.