Novel miniaturized neurotool for ultrasound brain stimulation Non-invasive ultrasound stimulation is a promising modality because of its competitive advantages such as focusing capability, beam steering precision, and long-term safety. While current transcranial ultrasound stimulation for small animals during in -vivo experiments is limited to acute stimulation anesthesia in stereotaxic fixation, with the newly d...

Crowd-sourced cognitive mapping: A new way of displaying people’s cognitive perception of urban space A crowd-sourced cognitive map – a novel method to create a visual representation of urban identity – was developed. By utilizing cognitive mapping and georeferenced text data, the new visualization combines the advantages of both conventional and state-of-the art research techniques to ...

Blood-based multiplexed diagnostic sensor helps to accurately detect alzheimer’s disease   A research team at KAIST reported a clinically accurate multiplexed electrical biosensor array for detecting Alzheimer’s disease with densely aligned single-walled carbon nanotube thin films. The sensor shows an average sensitivity of 90.0%, a selectivity of 90.0%, and an accuracy of 88.6%.   Article&nb...

Predicting the key actions that lead a robot to accomplish a task using deep learning   In reinforcement learning, a reinforcement signal may be infrequent and delayed, not appearing immediately after the action that triggered the reward. A novel method to detect the key action, defined as the most important action contributing to accomplishing a task, is proposed using deep neural networks. With the detecte...

Reinforcement learning algorithms tell us about how the human brain implements meta-reinforcement learning   Meta-reinforcement learning algorithms help us understand how the human brain learns to resolve complexity and uncertainty of the task. This study provides a glimpse of how it might ultimately be possible to use computational models to reverse engineer human reinforcement learning.   Article ...

I-Keyboard : fully imaginary keyboard on touch devices empowered by a deep neural decoder   An I-Keyboard – a fully imaginary keyboard on touch devices empowered by a deep neural decoder – was developed. The invisibility of I-Keyboard maximizes the usability of mobile devices, and the decoder allows users to start typing from any position on a touch screen at any angle without any calib...