QFALT: Quantization and Fault Aware Loss for Training Enables Performance Recovery with Unreliable Weights
Anmol Biswas, Udayan Ganguly · 2024
Deep Learning is the dominant method for classification and pattern recognition tasks. Traditionally, this entails running large, high-precision models on the cloud. However, there is an increasing demand for efficient, lightweight inference using compact models on low-power devices for edge Artificial Intelligence (AI) purposes. This necessitates highly quantized models. The task of effectively quantizing a deep-learning model is not trivial and many approaches have been proposed. In this paper, we propose a regularization-based technique to perform quantization-aware training. We validate our method by training Fully connected and Convolutional Neural Networks on the Fashion-MNIST, CIFAR-10, and CIFAR-100 datasets, showing under 1% degradation in classification accuracy for 2-bit and 3-bit quantized weight models compared to the 32-bit floating-point baseline. We also show the flexibility of our regularization function to train the network in a fault-aware manner, such that the degradation in performance caused by the presence of stuckat-0 faults making certain weight states unreachable is effectively halved, even for a high level of faulty bits (10%) and low level of quantization (3-bit). This opens up possibilities of improved fault and variability-aware training for low-power and low bit-precision neuromorphic devices.