Page 4: Research news on Artificial intelligence

Artificial intelligence, as a technique, refers to computational methods that enable machines to perform tasks that typically require human cognitive capabilities, such as perception, reasoning, learning, and decision-making. Core AI techniques include search and optimization algorithms, symbolic reasoning and knowledge representation, probabilistic inference, and machine learning approaches such as supervised, unsupervised, and reinforcement learning. These techniques often rely on statistical modeling, function approximation, and gradient-based optimization to construct models that generalize from data. AI techniques are implemented in software frameworks, integrated into pipelines for training, validation, and deployment, and are evaluated using task-specific performance metrics and robustness assessments.

AI improves flood projections under climate change

When engineers and planners design roads, bridges and dams, they rely on hydrological models intended to protect infrastructure and communities from 50- and 100-year floods. But as climate change increases the frequency and ...

AI boosts bird sound identification accuracy

In a study conducted at the University of Helsinki, AI was trained to classify bird sounds with increasing accuracy. The results of the study have been used, among others, in the "Muuttolintujen kevät" (Spring of Migratory ...

page 4 from 33