Scientists have discovered how to create circuits that are so small they’re invisible to the naked eye using a process that is both precise and economical for manufacturing. 

Perimetry (visual field testing) quantifies a patient’s retinal sensitivity to light and clarifies a deviation from normal retinal sensitivity. Visual field tests generally require high patient concentration, which can be exhausted. We constructed a framework for deep reinforcement learning to train ViFT (Visual Field Transformer), which controls all processes of visual field testing. ViFT achieves the same or higher accuracy than the state-of-the-art strategies, with less than half the test time of the state-of-the-art strategies.

The University of Osaka D3 Center will begin trial operations of the “Osaka University Compute and sTOrage Platform Urging open Science” (OCTOPUS), a computational and data platform promoting open science built by NEC Corporation (NEC; TSE: 6701), starting this September, with full-scale operations commencing in December.

Optical synapses have an ability to perceive and remember visual information, making them expected to provide more intelligent and efficient visual solutions for humans. As a new type of artificial visual sensory devices, photoelectric memristors can fully simulate synaptic performance and have great prospects in the development of biological vision. However, due to the urgent problems of nonlinear conductance and high-energy consumption, its further application in high-precision control scenarios and integration is hindered. In this work, we report an optoelectronic memristor with a structure of TiN/CeO₂/ZnO/ITO/Mica, which can achieve minimal energy consumption (187 pJ) at a single pulse (0.5 V, 5 ms). Under the stimulation of continuous pulses, linearity can be achieved up to 99.6%. In addition, the device has a variety of synaptic functions under the combined action of photoelectric, which can be used for advanced vision. By utilizing its typical long-term memory characteristics, we achieved image recognition and long-term memory in a 3 × 3 synaptic array and further achieved female facial feature extraction behavior with an activation rate of over 92%. Moreover, we also use the linear response characteristic of the device to design and implement the night meeting behavior of autonomous vehicles based on the hardware platform. This work highlights the potential of photoelectric memristors for advancing neuromorphic vision systems, offering a new direction for bionic eyes and visual automation technology.

Exoskeletons typically work by implementing motions programmed in advance and having the user call for them, making it difficult to use them for a wide range of motions in real-life environments. Now, in a notable example for wearable robotics, published in npj Robotics, researchers from the RIKEN Guardian Robot Project in Japan have used artificial intelligence to better assist users, by designing an exoskeleton that functions based on inputs regarding the user’s status as well as a view of the environment based on the user’s perspective.