HomeTechnologyULP Artificial Synapse for Next-generation AI Systems

    ULP Artificial Synapse for Next-generation AI Systems

    Brain-inspired computing is a promising candidate for next-generation computing technologies. Developing next-generation advanced artificial intelligence (AI) systems that can be as energy-efficient, lightweight, and adaptable as the human brain has attracted significant interest.

    “However, mimicking the brain’s neuroplasticity, which is the ability to change a neural network connection, in traditional artificial synapses using ultralow energy is extremely challenging,” said Desmond Loke, assistant professor at the Singapore University of Technology and Design (SUTD).

    An artificial synapse—comprising a gap across two neurons to allow electrical signals to pass and communicate with each other—can emulate the efficient neural signal transmission and memory formation process of the brain.

    To improve the energy efficiency of the artificial synapse, Loke’s research team has introduced a nanoscale deposit-only-metal-electrode fabrication process for artificial synapse for the first time. By using deposit-only nanopillar-based germanium-antimony-telluride memristive devices, the team designed a phase-change artificial synaptic device that has achieved an all-time-low energy consumption of 1.8 pJ per pair-pulse-based synaptic event. This is about 82% smaller compared to traditional artificial synapses.

    “The experiments have demonstrated that the artificial synapse based on phase-change materials could perform pair-pulse facilitation/depression, long-term potentiation/depression, and spike-timing-dependent plasticity with ultralow energies. We believe our finding can provide a promising approach for developing faster, larger scale artificial synapse arrays with significantly improved performance in AI tasks,” said Loke.

    Traditional heater electrodes formed by the deposited and etched process can cause/create a large degree of damage at the interfaces. Alternatively, the heater electrodes created by a deposit-only process in this study could create a smaller degree of damage at the interface. This may lead to a more robust, defect-free interface with substantially decreased contact resistance and its variations, consequently resulting in decreased operating current.

    Devendra Kumar
    Devendra Kumarhttps://www.eletimes.ai
    Devendra Kumar is the editor in chief of ELE Times. With over 25 years experience covering the electronics and application industry, Devendra has at various times focused on electronics, covering the global electronics industry with a particular focus on India His beat has always been emerging technologies and business models that enable a new generation of core electronics. In addition, he covers automotive, Internet of Things, and wireless/networking for ELE Times.

    Related News

    Must Read

    Thermal Management in 3D-IC: Modelling Hotspots, Materials, & Cooling Strategies

    Courtesy: Cadence As three-dimensional integrated circuit (3D-IC) technology becomes the...

    Keysight Launches AI Inference Emulation Platform to Validate and Optimise AI Infrastructure

    Keysight Technologies has introduced Keysight AI Inference Builder (KAI Inference...

    STMicroelectronics accelerates global adoption and market growth of Physical AI with NVIDIA

    STMicroelectronics announced the acceleration of global development and adoption...

    EDOM Technology Strengthens Its Role in Integrating the Physical AI Ecosystem

    EDOM Technology continues to expand its edge computing and...

    Indian HVAC Market Poised to Double in Five Years with 15% Annual Growth

    Industry leaders at ACREX India 2026 highlight that the...

    Smart EV Charging in India: How AI and ML Are Optimising Grid, Pricing and Reliability

    India’s electric mobility transition is entering a decisive phase....

    Milestone Systems Redefines the Open Platform for an AI-Native Era

    Milestone Systems has announced significant advancements to its XProtect...