Logo

SemiVoice

Recent #Neuromorphic Computing news in the semiconductor industry

azonano
3 months ago

Hexagonal Boron Nitride Atomristors: A Low-Power Solution for Neuromorphic Computing

➀ This study explores hexagonal boron nitride (h-BN) atomristors for their potential in energy-efficient neuromorphic computing;

➁ The researchers demonstrate the large memory window, low leakage current, and minimal power consumption of h-BN atomristors;

➂ The study highlights the potential of h-BN for high-performance applications in neuromorphic computing systems.

Neuromorphic ComputingPower Consumption
idw-online
6 months ago

Ilmenau School of Green Electronics: TU Ilmenau Develops Sustainable IT of the Future

➀ The Technische Universität Ilmenau launches the 'Ilmenau School of Green Electronics' to develop climate-neutral information technology; ➁ The project is funded by the Carl-Zeiss-Stiftung with nearly 5.2 million euros over four years; ➂ The initiative focuses on energy-efficient computing and bio-inspired microelectronics, aiming to reduce the environmental impact of IT hardware.
Climate ChangeNeuromorphic ComputingResource EfficiencyUniversityeducationelectronicsenergy efficiencyfundinghardwareinnovationresearch
idw-online
6 months ago

Karlsruhe University of Applied Sciences Collaborates with Mercedes-Benz on Next-Generation Autonomous Driving

➀ The Karlsruhe University of Applied Sciences (HKA) is supporting Mercedes-Benz in the development of autonomous driving with a focus on the enhancement of complex camera technologies in neuromorphic computing. ➁ The collaboration aims to advance intelligent mobility technologies, including neuromorphic computing, which mimics the human brain for more energy-efficient and faster AI calculations. ➃ Event cameras, a key component of neuromorphic computing, are being developed to provide real-time visual information to autonomous systems, significantly reducing reaction time compared to current camera systems.
Autonomous DrivingCamera TechnologyNeuromorphic Computing
idw-online
6 months ago

Dr. habil. Thomas Kämpfe Appointed Professor at Technical University of Braunschweig

➀ Dr. habil. Thomas Kämpfe has been appointed as a professor at the Technical University of Braunschweig's Faculty of Electrical Engineering, Information Technology, and Physics, taking over the chair for Neuromorphic Computing. ➁ He has a diverse research background in nanoelectronics and ferroelectronics, and has made significant contributions to in-memory computing with his habilitation research on ferroelectric hafnium oxide. ➃ Kämpfe's research and teaching experience will enhance the development of energy-efficient AI transistors at the CMOS Design Institute.
Fraunhofer InstituteHPCMicroelectronicsNeuromorphic Computingeducation
azonano
6 months ago

Memristor Devices Could Power the Next Generation of Neuromorphic Computers

➀ A novel memristor device with metal, dielectric, and metal layers can remember the history of electrical signals sent through it, potentially serving as the basis for neuromorphic computers; ➁ These devices exhibit analog behavior, storing information between 0 and 1 and emulating brain synapse functions; ➂ The interface between metal and dielectric layers is crucial for stable switching and enhanced performance, leading to improved image recognition in simulations.
AINeuromorphic Computing
weixin
7 months ago

IBM's New Chip Outperforms GPUs

➀ IBM's researchers are inspired by the human brain to develop neuromorphic computing, aiming to mimic the brain's efficiency in processing vast amounts of data required for tasks like AI.

➁ The concept of neuromorphic computing involves designing a computing system that reflects the efficiency of the human brain, which consumes very little power and solves tasks effectively even with ambiguous or undefined data.

➂ IBM's NorthPole chip, an example of neuromorphic architecture, integrates memory and computation on the same chip to overcome the von Neumann bottleneck and reduce energy consumption.

➃ IBM's research teams are working on materials and algorithms to improve the performance and efficiency of neuromorphic chips, with the goal of creating more powerful and energy-efficient AI accelerators.

AI acceleratorsNeuromorphic Computingibm
azonano
8 months ago

Advances in Nanoscale Manipulation Transform Electronic Devices

➀ A research team at Oak Ridge National Laboratory has developed a novel technique for creating precise atomic arrangements in ferroelectrics; ➁ The technique uses an electric stylus to alter electric dipoles in selected directions; ➂ This advancement could lead to low-power nanoelectronics and high-speed broadband communications for the 6G era; ➃ The research could significantly enhance the processing power and efficiency of future computing systems.
Neuromorphic Computingsemiconductor
azonano
10 months ago

Ultra-Low Power Synaptic Arrays for Neuromorphic Computing

➀ Researchers from China developed ultra-low-power carbon nanotube/porphyrin synaptic arrays with persistent photoconductivity for neuromorphic computing. ➁ These arrays mimic biological synapses, enhancing the performance of artificial neural networks. ➂ The devices showed stable performance across a wide temperature range and high prediction accuracy in autonomous vehicle navigation tasks.
Carbon NanotubesNeuromorphic ComputingSynaptic Arrays
businesskorea
11 months ago

Korean Researchers Discover Method to Enhance Next-Gen. Neuromorphic Computer Performance

1. Korean researchers have developed a method to enhance the reliability and commercialization of next-generation neuromorphic computing devices. 2. The method involves a heterovalent ion doping technique that improves device uniformity and performance. 3. This advancement can contribute to the commercialization of neuromorphic computing based on memristors, which are memory devices that retain all previous states.
AI OperationsMemory DevicesNeuromorphic Computing