Prism adaptation is a method for studying visuomotor plasticity in healthy individuals, as well as for rehabilitating patients suffering spatial neglect. We developed a new set-up based on virtual-reality (VR) and haptic-robotics allowing us to induc...
Existing adaptive locomotion control mechanisms for legged robots are usually aimed at one specific type of adaptation and rarely combined with others. Adaptive mechanisms thus stay at a conceptual level without their coupling effect with other mecha...
Learning knowledge or skills usually is considered to be based on the formation of an adequate internal mental model as a specific type of mental network. The learning process for such a mental model conceptualised as a mental network, is a form of (...
The intrinsic electrophysiological properties of single neurons can be described by a broad spectrum of models, from realistic Hodgkin-Huxley-type models with numerous detailed mechanisms to the phenomenological models. The adaptive exponential integ...
Three important systems, genes, the brain, and artificial intelligence (especially deep learning) have similar goals, namely, the maximization of likelihood or minimization of cross-entropy. Animal brains have evolved through predator-prey interactio...
Proceedings of the National Academy of Sciences of the United States of America
Dec 29, 2020
An important aspect of intelligence is the ability to adapt to a novel task without any direct experience (zero shot), based on its relationship to previous tasks. Humans can exhibit this cognitive flexibility. By contrast, models that achieve superh...
Hysteresis is a well-known phenomenon in physics that relates changes in a system with its prior history. It is also part of human visual experience (perceptual hysteresis), and two different neural mechanisms might explain it: persistence (a cause o...
Neural networks : the official journal of the International Neural Network Society
Sep 1, 2020
Visual trackers using deep neural networks have demonstrated favorable performance in object tracking. However, training a deep classification network using overlapped initial target regions may lead an overfitted model. To increase the model general...
Motion recognition and information interaction sensors with flexibility and stretchability are key functional modules as interactive media between the mechanical motions and electric signals in an intelligent robotic and rehabilitation training syste...
Attempting to imitate the brain's functionalities, researchers have bridged between neuroscience and artificial intelligence for decades; however, experimental neuroscience has not directly advanced the field of machine learning (ML). Here, using neu...