logo
Redefining the transistor: The ideal building block for artificial intelligence

Redefining the transistor: The ideal building block for artificial intelligence

SINGAPORE, March 28, 2025 /PRNewswire/ -- The team led by Associate Professor Mario Lanza from the Department of Materials Science and Engineering in the College of Design and Engineering at the National University of Singapore, has just revolutionised the field of neuromorphic computing by inventing a new super-efficient computing cell that can mimic the behaviour of both electronic neurons and synapses. The work, titled " Synaptic and neural behaviours in a standard silicon transistor" was published in the scientific journal Nature on 26 March 2025 and is already attracting interest from leading companies in the semiconductor field.
Electronic neurons and synapses are the two fundamental building blocks of next-generation artificial neural networks. Unlike traditional computers, these systems process and store data in the same place, eliminating the need to waste time and energy transferring data from memory to the processing unit (CPU). The problem is that implementing electronic neurons and synapses with traditional silicon transistors requires interconnecting multiple devices — specifically, at least 18 transistors per neuron and 6 per synapse. This makes them significantly larger and more expensive than a single transistor.
The team led by Professor Lanza has found an ingenious way to reproduce the electronic behaviours characteristic of neurons and synapses in a single conventional silicon transistor. The key lies in setting the resistance of the bulk terminal to a specific value to produce a physical phenomenon called 'impact ionisation,' which generates a current spike very similar to what happens when an electronic neuron is activated. Additionally, by setting the bulk resistance to other specific values, the transistor can store charge in the gate oxide, causing the resistance of the transistor to persist over time, mimicking the behaviour of an electronic synapse. Making the transistor operate as a neuron or synapse is as simple as selecting the appropriate resistance for the bulk terminal. The physical phenomenon of 'impact ionisation' had traditionally been considered a failure mechanism in silicon transistors, but Professor Lanza's team has managed to control it and turn it into a highly valuable application for the industry.
This discovery is revolutionary because it allows the size of electronic neurons to be reduced by a factor of 18 and that of synapses by a factor of 6. Considering that each artificial neural network contains millions of electronic neurons and synapses, this could represent a huge leap forward in computing systems capable of processing much more information while consuming far less energy. Furthermore, the team has designed a cell with two transistors — called Neuro-Synaptic Random Access Memory (NSRAM) — that allows switching between operating modes (neuron or synapse), offering great versatility in manufacturing since both functions can be reproduced using a single block, without the need to dope the silicon to achieve specific substrate resistance values.
The transistors used by Professor Lanza's team to implement these advanced neurons and synapses are not cutting-edge transistors like those manufactured in Taiwan or Korea, but rather traditional 180-nanometer node transistors, which can be produced by Singapore-based companies. According to Professor Lanza, 'once the operating mechanism is discovered, it's now more a matter of microelectronic design'.
The first author of the paper, Dr Sebastián Pazos, who is from King Abdullah University of Science and Technology, commented, 'Traditionally, the race for supremacy in semiconductors and artificial intelligence has been a matter of brute force, seeing who could manufacture smaller transistors and bear the production costs that come with it. Our work proposes a radically different approach based on exploiting a computing paradigm using highly efficient electronic neurons and synapses. This discovery is a way to democratise nanoelectronics and enable everyone to contribute to the development of advanced computing systems, even without access to cutting-edge transistor fabrication processes.'

Orange background

Try Our AI Features

Explore what Daily8 AI can do for you:

Comments

No comments yet...

Related Articles

Protegrity Founder Ulf Mattsson Joins Trust3 AI's Advisory Board
Protegrity Founder Ulf Mattsson Joins Trust3 AI's Advisory Board

Yahoo

time27 minutes ago

  • Yahoo

Protegrity Founder Ulf Mattsson Joins Trust3 AI's Advisory Board

SAN FRANCISCO, June 10, 2025 /PRNewswire/ -- Trust3 AI is proud to announce that Ulf Mattsson, a renowned pioneer in data security and Chief Security Strategist at Protegrity, has joined its Advisory Board. Mattsson brings unparalleled expertise in cybersecurity and privacy, including a legacy of innovation in advanced data protection, to Trust3 AI. Ulf Mattsson's career spans decades of groundbreaking contributions to data security. He is the inventor of Protegrity Vaultless Tokenization, a revolutionary approach to protecting sensitive information. Mattsson created the initial architecture of Protegrity's security framework, which became a standard among enterprise security protocols. With more than 70 awarded or issued U.S. patents under his name, Mattsson's work has served enterprise clients worldwide in safeguarding their critical information. Throughout his illustrious career, Mattsson has held pivotal leadership roles, including Head of Innovation at TokenEx, Chief Technology Officer at Atlantic BT, and earlier CTO at Compliance Engineering. He has collaborated on joint software projects with world-class research and development teams at major tech companies like IBM, Microsoft, Hewlett-Packard, Oracle, and RSA Security. Trust3 AI will leverage Mattsson's deep expertise to strengthen its mission of delivering state-of-the-art AI solutions equipped with robust security and governance capabilities. Known for building frameworks that prioritize safety, privacy, and compliance in rapidly evolving technology landscapes, Mattsson's involvement marks a significant milestone for Trust3 AI as it advances its platform for AI application governance. Ulf's unmatched expertise in data security and privacy engineering is a game-changer for us," said Neeraj Sabharwal, Co-Founder of Trust3 AI. "His track record of building scalable, secure systems aligns perfectly with our mission to make AI adoption safer, more transparent, and enterprise-ready. With Ulf on board, we're accelerating our vision for a unified trust layer that empowers responsible AI innovation. Founded on the principles of precision, security, and innovation, Trust3 AI is redefining AI governance and application safety. With Mattsson's advisory guidance, Trust3 AI is positioned to tackle security and policy challenges at the forefront of AI development while driving groundbreaking solutions tailored to enterprise needs. About Trust3 AI Based in San Francisco, Trust3 AI (formerly PAIG AI) is a leader in AI governance, security, and lifecycle management solutions. Trust3 AI's unified platform empowers businesses to adopt AI responsibly by building trust into every AI interaction. Trust3 AI is trusted by organizations across industries, from healthcare to finance, and is proud to be part of the Snowflake and Databricks startup accelerator programs. For more information, visit and follow us on Linkedin For media inquiries, please contact: Media Relations media@ View original content: SOURCE Trust3 AI Error in retrieving data Sign in to access your portfolio Error in retrieving data Error in retrieving data Error in retrieving data Error in retrieving data

GT Medical Technologies Names James Leech Chief Financial and Strategy Officer
GT Medical Technologies Names James Leech Chief Financial and Strategy Officer

Yahoo

timean hour ago

  • Yahoo

GT Medical Technologies Names James Leech Chief Financial and Strategy Officer

Experienced Life Sciences Executive Joins Leadership Team as Company Further Advances Commercialization of GammaTile® TEMPE, Ariz., June 10, 2025 /PRNewswire/ -- GT Medical Technologies, a medical device company with a corporate purpose of improving the lives of patients with brain tumors, today announced that James Leech, a seasoned financial and operational life sciences leader, has joined the company as Chief Financial and Strategy Officer. "We are excited to welcome James as he assumes the Chief Financial and Strategy Officer role at GT Medical Technologies," said Per Langoe, CEO of GT Medical Technologies. "I look forward to collaborating with him to ensure even more doctors and patients have access to GammaTile®. With over 10 years of successful experience leading commercial-stage healthcare-focused companies in an advisory and operational capacity, his expertise on a range of traditional and complex financial and strategic management areas provides us with a substantial opportunity for continued growth and adoption." Mr. Leech will work across the team to accelerate commercial opportunities for GammaTile while spearheading corporate strategy and development, as well as financial and investor management. "I look forward to joining a leadership team that is dedicated to transforming the lives of patients with brain tumors," said Mr. Leech. "GT Medical Technologies is poised for significant growth, and I am thrilled to collaborate with all stakeholders to optimize the company's continued expansion of GammaTile, our FDA-cleared bioresorbable radiotherapy implant for the treatment of brain tumors." Mr. Leech has considerable experience leading businesses from inception through hyper growth phases of their life cycle. He has advised and worked across the life science industry with direct experience in MedTech, healthcare services, and biopharmaceutical sectors across all major therapeutic areas. Previously, Mr. Leech was the Chief Financial and Strategy Officer of Moximed, a commercial-stage orthopedic device company. Prior to Moximed, Mr. Leech was the Chief Business Officer at Palette Life Sciences from the Company's inception through its acquisition by Teleflex, Inc. Mr. Leech started his career in life science investment banking and strategy consulting. He brings significant cross-border experience, having executed transactions and operational initiatives on behalf of and involving companies across the EU and APAC. GammaTile is an innovative form of radiation therapy placed at the time of tumor removal surgery, delivering immediate, targeted radiation to the tumor site when cancer cells are most vulnerable. Unlike conventional approaches, which at their lowest often require a delay between surgery and radiation therapy to allow for wound healing, GammaTile eliminates this treatment gap. By delivering immediate, localized radiation directly at the tumor site, it is designed to maximize the treatment's effectiveness against remaining cancer cells and reduce the risk of regrowth.1 About GT Medical Technologies, Medical Technologies was founded by a dedicated team of brain tumor specialists to address unmet needs in brain tumor treatment. The company is committed to improving the lives of patients with brain tumors through innovative solutions that elevate the standard of care. About GammaTileGammaTile is an FDA-cleared, bioabsorbable collagen implant embedded with radiation seeds, designed for patients with operable brain tumors. By delivering radiation directly from within—placed into the surgical cavity at the time of tumor removal—GammaTile provides immediate, localized treatment. This approach targets remaining cancer cells when they are most vulnerable to help prevent regrowth, while minimizing radiation exposure to healthy brain tissue. Since its full market launch in the United States in March 2020, GammaTile has been adopted by more than 100 leading centers, underscoring its growing acceptance in both academic and community healthcare settings. For more information, visit and follow @GammaTile on Facebook, Instagram, LinkedIn and X. Media ContactDawn FallonNew Dawn Communications LLCDfallon@ References Garcia MA et al. J Neurooncol. 166:203-212 (2024). View original content to download multimedia: SOURCE GT Medical Technologies

AI Boom Propels Server and Storage Components to 62 Percent Growth in 1Q 2025, According to Dell'Oro Group
AI Boom Propels Server and Storage Components to 62 Percent Growth in 1Q 2025, According to Dell'Oro Group

Yahoo

timean hour ago

  • Yahoo

AI Boom Propels Server and Storage Components to 62 Percent Growth in 1Q 2025, According to Dell'Oro Group

Surging Demand for Accelerators, HBM, and NICs Underpins Record Expansion Across the AI Infrastructure Stack REDWOOD CITY, Calif. , June 10, 2025 /PRNewswire/ -- According to a recently published report by Dell'Oro Group, the trusted source for market information about the telecommunications, security, networks, and data center industries, the on-going AI expansion cycle drove the server and storage component market to 62 percent year-over-year growth in 1Q 2025. The surging demand for accelerators, HBM, and NICs underpins record expansion across the AI infrastructure stack. "The AI accelerator market was led by robust uptake of NVIDIA's Blackwell GPU platform as well as the continued rollout of custom accelerators by major cloud service providers," said Baron Fung, Senior Research Director at Dell'Oro Group. "We estimate Blackwell has already surpassed an estimated 50 percent of the company's high-end GPU shipments during the quarter, which in turn is prompting upgrades in networking, storage, and infrastructure across the data center. "Meanwhile, custom silicon continues to gain traction with hyperscalers expanding their deployment of custom accelerators for both training and inference of large foundational models. Beyond AI-specific hardware, general-purpose components such as CPUs, memory, storage drives, and NICs also saw meaningful growth in early 2025. This was partly driven by a recovery in mainstream enterprise server demand, as well as inventory builds and component price hikes ahead of the anticipated expiration of the 90-day reciprocal tariff pause," Fung added. Additional highlights from the 1Q 2025 Data Center IT Semiconductors and Components Quarterly Report: The Server and Storage Systems Component market is forecast to grow by over 50 percent in 2025 despite tariff-related uncertainties. SK Hynix led the HBM market with a 64 percent revenue share, followed by Samsung and Micron. ARM CPUs now hold 25 percent of the server market, driven by the NVIDIA GB200 Blackwell ramp and hyperscaler custom deployments. Smart NIC and DPU revenues increased by 71 percent because of strong deployment of Ethernet adapters in AI clusters. About the Report Dell'Oro Group's Data Center IT Semiconductors and Components Quarterly Report tracks revenue, unit and capacity shipments and unit and capacity pricing, along with market share of major semiconductor and component manufacturers that supplies into the data center server and storage system markets starting from 2018. Technology of focus will be major server and storage semiconductors and components such as CPUs, accelerators such as GPUs, FPGAs, and custom AI ASICs, Ethernet Adapters and Smart NICs, HBM and DRAM, and HDDs and NAND/SSDs. In addition, we will provide a forecast of the demand for these components based on shipments of servers and storage system to the hyperscale cloud service providers and to the rest-of-the-market. To purchase this report, please contact us at dgsales@ About Dell'Oro Group Dell'Oro Group is a market research firm that specializes in strategic competitive analysis in the telecommunications, security, enterprise networks infrastructure, and data center markets. Our firm provides in-depth quantitative data and qualitative analysis to facilitate critical, fact-based business decisions. For more information, contact Dell'Oro Group at +1.650.622.9400 or visit View original content to download multimedia: SOURCE Dell'Oro Group

DOWNLOAD THE APP

Get Started Now: Download the App

Ready to dive into the world of global news and events? Download our app today from your preferred app store and start exploring.
app-storeplay-store