The Implications Of AI Everywhere: From Data Center To Edge


Generative AI has upped the ante on the transformative force of AI, driving profound implications across all aspects of our everyday lives. Over the past year, we have seen AI capabilities placed firmly in the hands of consumers. The recent news and product announcements emerging from MWC 2024 highlighted what we can expect to see from the next wave of generative AI applications. AI will be eve... » read more

RISC-V Ultra-Low-Power Edge Accelerators (EPFL)


A technical paper titled “X-HEEP: An Open-Source, Configurable and Extendible RISC-V Microcontroller for the Exploration of Ultra-Low-Power Edge Accelerators” was published by researchers at EPFL. Abstract: "The field of edge computing has witnessed remarkable growth owing to the increasing demand for real-time processing of data in applications. However, challenges persist due to limitat... » read more

Modeling Compute In Memory With Biological Efficiency


The growing popularity of generative AI, which uses natural language to help users make sense of unstructured data, is forcing sweeping changes in how compute resources are designed and deployed. In a panel discussion on artificial intelligence at last week’s IEEE Electron Device Meeting, IBM’s Nicole Saulnier described it as a major breakthrough that should allow AI tools to assist huma... » read more

Data Formats For Inference On The Edge


AI/ML training traditionally has been performed using floating point data formats, primarily because that is what was available. But this usually isn't a viable option for inference on the edge, where more compact data formats are needed to reduce area and power. Compact data formats use less space, which is important in edge devices, but the bigger concern is the power needed to move around... » read more

Maximizing Edge Intelligence Requires More Than Computing


By Toshi Nishida, Avik W. Ghosh, Swaminathan Rajaraman, and Mircea Stan Commercial-off-the-shelf (COTS) components have enabled a commodity market for Wi-Fi-connected appliances, consumer products, infrastructure, manufacturing, vehicles, and wearables. However, the vast majority of connected systems today are deployed at the edge of the network, near the end user or end application, opening... » read more

Data Collection For Edge AI / Tiny ML With Sensors


Reality AI software from Renesas provides solution suites and tools for R&D engineers who build products and internal solutions using sensors. Working with accelerometers, vibration, sound, electrical (current/voltage/ capacitance), radar, RF, proprietary sensors, and other types of sensor data, Reality AI software identifies signatures of events and conditions, correlates changes in signat... » read more

Patterns And Issues In AI Chip Design


AI is becoming more than a talking point for chip and system design, taking on increasingly complex tasks that are now competitive requirements in many markets. But the inclusion of AI, along with its machine learning and deep learning subcategories, also has injected widespread confusion and uncertainty into every aspect of electronics. This is partly due to the fact that it touches so many... » read more

Analog Circuits Enabling Learning in Mixed-Signal Neuromorphic SNNs, With Tristate Stability and Weight Discretization Circuits


A technical paper titled “Neuromorphic analog circuits for robust on-chip always-on learning in spiking neural networks” was published by researchers at University of Zurich and ETH Zurich. Abstract: "Mixed-signal neuromorphic systems represent a promising solution for solving extreme-edge computing tasks without relying on external computing resources. Their spiking neural network circui... » read more

Analog On-Chip Learning Circuits In Mixed-Signal Neuromorphic SNNs


A technical paper titled "Neuromorphic analog circuits for robust on-chip always-on learning in spiking neural networks" was published by researchers at Institute of Neuroinformatics, University of Zurich, and ETH Zurich. Abstract: "Mixed-signal neuromorphic systems represent a promising solution for solving extreme-edge computing tasks without relying on external computing resources. Their s... » read more

Edge Computing: Four Smart Strategies For Safeguarding Security And User Experience


It is a brave new world for enterprise networks. Smart devices are getting smarter, and edge computing is emerging as a viable way to reduce latency and improve performance. But as network architectures grow increasingly amorphous, what kind of impact will this have on security and performance? Download this white paper to discover how you can boost security, ensure quality of service, and futu... » read more

← Older posts