11 February 2025 in Nature Communications
Neuromorphic computing shows promise for advancing computing efficiency and capabilities of AI applications using brain-inspired principles. However, the neuromorphic research field currently lacks standardized benchmarks, making it difficult to accurately measure technological advancements, compare performance with conventional methods, and identify promising future research directions. This article presents NeuroBench, a benchmark framework for neuromorphic algorithms and systems, which is collaboratively designed from an open community of researchers across industry and academia. NeuroBench introduces a common set of tools and systematic methodology for inclusive benchmark measurement, delivering an objective reference framework for quantifying neuromorphic approaches in both hardware-independent and hardware-dependent settings. For latest project updates, visit the project website (neurobench.ai).
2 January 2024 in Nature Communications
The brain’s connectivity is locally dense and globally sparse, forming a small-world graph—a principle prevalent in the evolution of various species, suggesting a universal solution for efficient information routing. However, current artificial neural network circuit architectures do not fully embrace small-world neural network models. Here, we present the neuromorphic Mosaic: a non-von Neumann systolic architecture employing distributed memristors for in-memory computing and in-memory routing, efficiently implementing small-world graph topologies for Spiking Neural Networks (SNNs). We’ve designed, fabricated, and experimentally demonstrated the Mosaic’s building blocks, using integrated memristors with 130 nm CMOS technology. We show that thanks to enforcing locality in the connectivity, routing efficiency of Mosaic is at least one order of magnitude higher than other SNN hardware platforms. This is while Mosaic achieves a competitive accuracy in a variety of edge benchmarks. Mosaic offers a scalable approach for edge systems based on distributed spike-based computing and in-memory routing.
11 April 2019 in IEEE Electron Device Letters
Thinning the semiconductor active layer thickness down to a level comparable with the carriers’ diffusion length while keeping its absorption high is an ultimate goal to boost the performance of optoelectronic devices. Strong interference in multilayer structures is one of the promising and practical solutions, owing to their simple and large-scale compatible fabrication route. These nanocavity designs not only provide near unity absorption, but they also can be designed in a way that a spectrally selective absorption response can be achieved. In this paper, we will demonstrate the functionality of a metal-insulator-semiconductor (MIS) cavity to obtain spectrally selective ultrathin photodetectors. To prove our theoretical and numerical findings, a 4 nm thick amorphous silicon (a-Si) based MIS cavity is designed, fabricated, and characterized. The experimental results show that the optimized cavity design can act as an efficient visible blind ultraviolet (UV) photodetector. The proposed design shows responsivity values of 120 mA/W and 2.5 mA/W in the UV (λ=350 nm) and visible (λ=500 nm) regions, respectively.
21 March 2023 in Research Square
The connectivity in the brain is locally dense and globally sparse - giving rise to a small-world graph. This is a principle that has persisted during the evolution of many species - indicating a universal solution to the efficient routing of information. However, existing circuit architectures for artificial neural networks neither leverage this organization nor do they efficiently support small-world neural network models. Here, we propose the neuromorphic Mosaic: a non-von Neumann systolic architecture that uses distributed memristors, not only for in-memory computing, but also for in-memory routing, to efficiently implement small-world graph topologies. We design, fabricate, and experimentally demonstrate the building blocks of this architecture, using integrated memristors with 130 nm CMOS technology. We demonstrate that neural networks implemented following this approach can achieve competitive accuracy figures compared to equivalent unconstrained and full-precision networks, for three real-time benchmarks: classification of electrocardiography signals, keyword spotting and motor control via reinforcement learning. The Mosaic shows improvements between one and four orders of magnitude, compared to other event-based neuromorphic architectures for routing events across the network. The Mosaic opens up a new scalable approach for designing edge AI systems based on distributed computing and in-memory routing, offering a natural platform onto which architectures inspired by biological nervous systems can be readily mapped.