The Marketing Minute: Cracking the Code of Technical Marketing
Trouble in Your Tank: Implementing Direct Metallization in Advanced Substrate Packaging
Nanoelectronics Collaboration Draws International Acclaim for Advances in Intelligent Autonomous Systems
January 30, 2017 | University of SouthamptonEstimated reading time: 1 minute
Transdisciplinary research, driven by expertise from Electronics and Computer Science (ECS) at the University of Southampton, has attracted global recognition for speeding the creation of intelligent autonomous systems.
The collaboration, which has successfully demonstrated unsupervised learning tasks that could be applied to powerful future devices, has been highlighted this winter in the international Nature Nanotechnology journal.
Researchers from Southampton’s Nanoelectronics and Nanotechnology research group have created a network of nanoscale devices – known as a memristors – that use unmanned machine learning protocols to observe and recognise letters of the alphabet, emulating the autonomous synoptic functions of the human brain.
The analog memristors, which have been developed with support of the EU-funded Real neurons-nanoelectronics Architecture with Memristive Plasticity (RAMP) project, have also been verified with noisy or incomplete input images.
Dr Themis Prodromakis, a Reader in Nanoelectronics at ECS and an Engineering and Physical Sciences Research Council (EPSRC) Fellow, said: “It is extremely satisfying to see the outcomes of our collaborative research programme highlighted in such a prestigious journal. The unsupervised learning demonstrated through the memristors’ image processing will have significant applications in future embedded systems used in the areas of big data and the Internet of Things.”
The recent Nature Nanotechnology journal highlight draws upon an article published in Frontiers of Neuroscience, entitled Analog Memristive Synapse in Spiking Networks Implementing Unsupervised Learning. The paper proposes a new analog memristor capable of pattern recognition after an unsupervised training process. These learning abilities would enable a new wave systems capable of performing tasks that would be difficult for conventional computing systems.
Share on:
Testimonial
"We’re proud to call I-Connect007 a trusted partner. Their innovative approach and industry insight made our podcast collaboration a success by connecting us with the right audience and delivering real results."
Julia McCaffrey - NCAB GroupSuggested Items
India’s Aerospace and Defence Engineered for Power, Driven by Electronics
09/16/2025 | Gaurab Majumdar, Global Electronics AssociationWith a defence budget of $82.05 billion (2025–26) and a massive $223 billion earmarked for aerospace and defence spending over the next decade, India is rapidly positioning itself as a major player in the global defence and aerospace market.
VIDEOTON EAS's Bulgarian Subsidiary Expands Into Automotive Products
09/15/2025 | VideotonVEAS Bulgaria, engaged in electronics manufacturing, has joined the ranks of VIDEOTON companies authorized to produce automotive products.
Variosystems Strengthens North American Presence with Southlake Relaunch 2025
09/15/2025 | VariosystemsVariosystems celebrated the relaunch of its U.S. facility in Southlake, Texas. After months of redesign and reorganization, the opening marked more than just the return to a modernized production site—it was a moment to reconnect with our teams, partners, and the local community.
Hanwha Aerospace to Collaborate with BAE Systems on Advanced Anti-jamming GPS for Guided Missiles
09/15/2025 | HanwhaHanwha Aerospace has signed a contract with BAE Systems to integrate next-generation, anti-jamming Global Positioning System (GPS) technology into Hanwha Aerospace’s Deep Strike Capability precision-guided weapon system.
EV Group Achieves Breakthrough in Hybrid Bonding Overlay Control for Chiplet Integration
09/12/2025 | EV GroupEV Group (EVG), a leading provider of innovative process solutions and expertise serving leading-edge and future semiconductor designs and chip integration schemes, today unveiled the EVG®40 D2W—the first dedicated die-to-wafer overlay metrology platform to deliver 100 percent die overlay measurement on 300-mm wafers at high precision and speeds needed for production environments. With up to 15X higher throughput than EVG’s industry benchmark EVG®40 NT2 system designed for hybrid wafer bonding metrology, the new EVG40 D2W enables chipmakers to verify die placement accuracy and take rapid corrective action, improving process control and yield in high-volume manufacturing (HVM).