Answers are grounded in this paper and cite their sources.
Monolithic arrays using ULTRARAM enhance training accuracy and energy efficiency in neural networks, implying significant advancements in memory technology.
The memory demands of large-scale deep neural networks (DNNs) require synaptic weight values to be stored and updated in off-chip memory, such as dynamic random-access memory, which reduces energy efficiency and increases training time. Monolithic crossbar or pseudo-crossbar arrays using analog non-volatile memories, which can store and update weights on-chip, present an opportunity to efficiently accelerate DNN training. In this article, we present on-chip training and inference of a neural network using an ULTRARAM memory device-based synaptic array and complementary metal–oxide–semiconductor (CMOS) peripheral circuits. ULTRARAM is a promising emerging memory exhibiting high endurance (>107 P/E cycles), ultrahigh retention (>1000 years), and ultralow switching energy per unit area. A physics-based compact model of ULTRARAM memory device has been proposed to capture the real-time trapping/de-trapping of charges in the floating gate and utilized for the synapse simulations. A circuit-level macro-model is employed to evaluate and benchmark the on-chip learning performance in terms of area, latency, energy, and accuracy of an ULTRARAM synaptic core. In comparison with CMOS-based design, it demonstrates an overall improvement in area and energy by 1.8× and 1.52×, respectively, with 91% of training accuracy.
No takes yet. Share an insight, caveat, or question.
Kumar et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: