architectures employing analogue inmemory computing techniques are being intensively investigated in pursuit of reducing energy consumption and latency. [1][2][3][4] Two-terminal memristors, owing to their dense device structure, ability to store and process data at the same location, simple weight update scheme, and straightforward vector-matrix multiplication (VMM) in a crossbar array fashion, have been widely explored for neuromorphic computing, machine learning, and edge computing applications. [5,6] To this end, various non-volatile memories (NVMs), including resistive memory, flash memory, phase-change memory, and magneto-resistive memory have been explored to carry out feature extraction, image processing, and neuro-inspired computing. [6][7][8][9][10][11][12][13][14] Ferroelectric resistive memory utilizes multi-domain polarization switching dynamics in a ferroelectric material, which has been shown to deliver fast potentiation and depression programming, symmetric and linear conductance response, and large ON/OFF conductance ratios. [15][16][17][18][19] To harness the well-established periphery circuitry and increase integration density, however, it is desired to integrate ferroelectric memory arrays with mainstream semiconductor technology, which significantly narrows down the materials available. [20][21][22] The discovery of ferroelectricity in HfO 2 -based materials has rejuvenated the interest in ferroelectric memory with both front-end-of-line and back-endof-line compatibility. To date, however, related two terminal resistive memories still suffer from low ON/OFF ratios, wakeup effect and significant imprint oscillations and retention loss. [19,21,[23][24][25][26][27] Although recent studies have shown that HfO 2based field effect transistors are much less affected by above limitations, [28] two-terminal memristors offer the advantages of significantly reduced device area and operation power and, therefore, have remained a subject of intensive study.Those issues can potentially be addressed by exploiting a new class of ferroelectrics -nitride ferroelectrics. [29] Sc-alloyed III-nitrides, i.e., ScAlN and ScGaN, have been discovered with giant remnant polarization and superior thermal stability. [29][30][31][32][33] The wide processing temperature window and the approximation of the lattice with other nitride materials promise good compatibility and seamless integration with both GaN and silicon technology. [34][35][36][37][38] In addition, the wake-up effect and Computing in the analog regime using nonlinear ferroelectric resistive memory arrays can potentially alleviate the energy constraints and complexity/footprint challenges imposed by digital von Neumann systems. Yet the current ferroelectric resistive memories suffer from either low ON/OFF ratios/imprint or limited compatibility with mainstream semiconductors. Here, for the first time, ferroelectric and analog resistive switching in an epitaxial nitride heterojunction comprising ultrathin (≈5 nm) nitride ferroelectrics, i.e., ScAlN, with poten...