Neuromorphic computing has been attracting ever‐increasing attention due to superior energy efficiency, with great promise to promote the next wave of artificial general intelligence in the post‐Moore era. Current approaches are, however, broadly designed for stationary and unitary assignments, thus encountering reluctant interconnections, power consumption, and data‐intensive computing in that domain. Reconfigurable neuromorphic computing, an on‐demand paradigm inspired by the inherent programmability of brain, can maximally reallocate finite resources to perform the proliferation of reproducibly brain‐inspired functions, highlighting a disruptive framework for bridging the gap between different primitives. Although relevant research has flourished in diverse materials and devices with novel mechanisms and architectures, a precise overview remains blank and urgently desirable. Herein, the recent strides along this pursuit are systematically reviewed from material, device, and integration perspectives. At the material and device level, we comprehensively conclude the dominant mechanisms for reconfigurability, categorized into ion migration, carrier migration, phase transition, spintronics, and photonics. Integration‐level developments for reconfigurable neuromorphic computing are also exhibited. Finally, a perspective on the future challenges for reconfigurable neuromorphic computing is discussed, definitely expanding its horizon for scientific communities.This article is protected by copyright. All rights reserved

No abstract

No abstract

For the first time, a configurable NbOx memristor is achieved that can be configured as an artificial synapse or neuron after fabrication by controlling the forming compliance current (FCC). When the FCC ≤ 2 mA, the memristors exhibit the resistive‐switching (RS) property, enabling multiple types of synaptic plasticity, including short‐term potentiation, paired‐pulse facilitation, short‐term memory, and long‐term memory. When the FCC ≥ 3 mA, the memristors can be electroformed and exhibit the threshold switching (TS) property with excellent endurance (>1012), thus achieving various biological neuron characteristics, such as threshold‐triggering, strength‐modulation of spike frequency, and leaky integrate‐and‐fire. This enables the successful implementation of a spiking Pavlov's dog that employs the spikes as information carrier by connecting an RS NbOx memristor as artificial synapse and a TS memristor as artificial neuron in series. Furthermore, a fully NbOx memristors‐based single‐layer spiking neural network is simulated. It is first found that, due to the forgetting property of synapse, the recognition accuracy for the Modified National Institute of Standards and Technology handwritten digits is increased from 85.49% to 91.45%. This study provides a solid foundation for the development of neuromorphic machines based on the principles of the human brain.

Traditional cooling methods for electronic chips cannot fully meet the increasing cooling requirement of chips with high heat flux at present, so finding high-efficiency and low-cost cooling functional materials, and cooling methods with high efficiency has been a hot spot to explore. In this article, using Fluent 6, we construct a grooved channel physical model and analyze cooling effects of ethylene glycol/water ice slurry as a functional material on the chips under conditions that baffle lengths are 60mm, 80mm and 90mm, the mass flow rates are 0.4kg/s, 0.3kg/s and 0.2kg/s, and the ice fractions are 15%, 20%, 25% respectively. The results show that the chip cooling rate is increasing effectively and the temperature uniformity is better as well as the utilization rate of the latent heat is increasing as the length of baffles, the mass flow rate and the ice fraction are increasing, but the pressure loss resulted from the local effects of the inlet and corners cannot be ignored. Considering the cooling effect and the uniformity of temperature field, the length of baffles should be 83%-93% of length of flow path. In practical projects, the temperature difference between inlet and outlet should be reduced and the diameter of pipes should be decreased in order to take full advantage of the huge latent heat of the ice slurry while the ice is completely melted. Therefore, ice slurry as a functional material has a great potential to cool high integrated electronic chips.