Abstract: In this paper, a second-order Volterra adaptive filtering algorithm based on natural gradient descent (SOVNGD) is proposed. Compared to the conventional second-order Volterra (SOV) algorithm ...

A novel gradient boosting framework that dynamically synthesizes features during training based on residual error patterns. Uses a meta-learning controller to ...

Abstract: Impedance control with fixed parameters lacks the flexibility to adapt to dynamic and uncertain environments, which may not meet the task requirements during robot-environment interaction.

Class Disrupted is an education podcast featuring author Michael Horn and Futre’s Diane Tavenner in conversation with ...

Sara Hooker, CEO of Adaption Labs, argues that the future of AI lies in adaptive learning rather than simply increasing model size.

Researchers have developed an advanced artificial intelligence (AI) framework designed to significantly improve the forecasting of carbon dioxide emissions in the aviation sector. ACGRIME is an ...

This study presents a bio-inspired control framework for soft robots, enhancing tracking accuracy by over 44% under disturbances while maintaining stability.

Advances in machine learning and shape-memory polymers are enabling engineers to design for mechanical performance first and ...

A new study introduces a global probabilistic forecasting model that predicts when and where ionospheric disturbances—measured by the Rate of total electron content (TEC) Index (ROTI)—are likely to ...

The researchers have developed a new approach to making biometric presentation attack detection (PAD) resistant to demographic bias.