Quantized Non-Volatile Nanomagnetic Synapse based Autoencoder for Efficient Unsupervised Network Anomaly Detection
Muhammad Sabbir Alam, Walid Al Misba, Jayasimha Atulasimha
在基于自动编码器的异常检测范式中,由于硬件、能源和计算资源有限,在能够实时学习的边缘设备中实现自动编码器极具挑战性。 我们通过设计基于低分辨率的非易失性内存突触的自动编码器并采用有效的量化神经网络学习算法来证明这些限制。 我们提出了一个铁磁赛道,工程缺口托管磁域壁(DW)作为自动解码器突触,其中有限状态(5态)突触重量由自旋轨道扭矩(SOT)电流脉冲操纵。 在NSL-KDD数据集上评估拟议自动编码器模型的异常检测性能。 执行自编码器的有限分辨率和DW器件随机性感知训练,与具有浮点精度重量的自动编码器产生可比的异常检测性能。 虽然已知纳米级设备中量化状态的有限数量和DW突触重量固有的随机性会对性能产生负面影响,但我们的硬件感知训练算法被证明利用这些不完美的设备特性来改进异常检测精度(90.98)
In the autoencoder based anomaly detection paradigm, implementing the autoencoder in edge devices capable of learning in real-time is exceedingly challenging due to limited hardware, energy, and computational resources. We show that these limitations can be addressed by designing an autoencoder with low-resolution non-volatile memory-based synapses and employing an effective quantized neural network learning algorithm. We propose a ferromagnetic racetrack with engineered notches hosting a magnet...