We demonstrate high accuracy classification for handwritten digits from the MNIST dataset (∼98.00%) and RGB images from the CIFAR-10 dataset (∼86.80%) by using resistive memories based on a 2D van-der-Waals semiconductor: hafnium disulfide (HfS2).These memories are fabricated via dry thermal oxidation, forming vertical crossbar HfOxSy/HfS2 devices with an highly-ordered oxide-semiconductor structure.Our devices operate without electroforming or current compliance and exhibit multi-state, non-volatile resistive switching, allowing resistance to be precisely tuned using voltage pulse trains.Using low-energy potentiation and depression pulses (0.7V-0.995V, 160ns-350ns), we achieve 31 (∼5 bits) stable conductance states with high linearity, symmetry, and low variation over 100 cycles.Key performance metrics-such as weight update, quantisation, and retention-are extracted from these experimental devices.These characteristics are then used to simulate neural networks with our resistive memories as weights.Neural networks are trained on state-of-theart (SOTA) digital hardware (CUDA cores) and a baseline inference accuracy is extracted.IBM's Analog Hardware Acceleration Kit (AIHWKIT) is used to modify and remap digital weights in the pretrained network, based on the characteristics of our devices.Simulations account for factors like conductance linearity, device variation, and converter resolution.In both image recognition tasks, we demonstrate excellent performance, similar to SOTA, with only <0.07% and <1.00% difference in inference accuracy for the MNIST and CIFAR-10 datasets respectively.The forming-free, compliance-free operation, fast switching, low energy consumption, and high accuracy classification demonstrate the strong potential of HfOxSy/HfS2-based resistive memories for energy-efficient neural network acceleration and neuromorphic computing.
The paper presents an innovative study on high-accuracy classification for handwritten digits and RGB images using HfO x S y /HfS 2 memristors. Utilizing the MNIST and CIFAR-10 datasets, classification accuracies reached approximately 98.00% and 86.80%, respectively. The devices demonstrated multi-state, non-volatile resistive switching and operated without electroforming or current compliance. Key metrics for performance were extracted and employed in neural network simulations. This research signifies a step toward energy-efficient neural network acceleration and offers promising results against state-of-the-art (SOTA) methods. The study highlights the advantages of memristive technology in overcoming limitations of traditional hardware for machine learning applications.
This paper employs the following methods:
- Resistive Random Access Memory (RRAM)
- Neural Networks
- Convolutional Neural Networks (CNN)
The following datasets were used in this research:
- MNIST classification accuracy: ∼98.00%
- CIFAR-10 classification accuracy: ∼86.80%
The authors identified the following limitations:
- Noise during conductance update or read steps
- Linear conductance update not achievable under all conditions
- Electroforming and current compliance challenges in some memristive devices
- Number of GPUs: 1
- GPU Type: NVIDIA RTX 3080
- Compute Requirements: 30 epochs