Benchmarking the Accuracy and Robustness of Feedback Alignment Algorithms

Abstract

Backpropagation is the default algorithm for training deep neural networks due to its simplicity, efficiency and high convergence rate. However, its requirements make it impossible to be implemented in a human brain. In recent years, more biologically plausible learning methods have been proposed. Some of these methods can match backpropagation accuracy, and simultaneously provide other extra benefits such as faster training on specialized hardware (e.g., ASICs) or higher robustness against adversarial attacks. While the interest in the field is growing, there is a necessity for open-source libraries and toolkits to foster research and benchmark algorithms. In this paper, we present BioTorch, a software framework to create, train, and benchmark biologically motivated neural networks. In addition, we investigate the performance of several feedback alignment methods proposed in the literature, thereby unveiling the importance of the forward and backward weight initialization and optimizer choice. Finally, we provide a novel robustness study of these methods against state-of-the-art white and black-box adversarial attacks.

References in corpus (18)

• Adam: A Method for Stochastic Optimization
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Towards Deep Learning Models Resistant to Adversarial Attacks
• Improving Reproducibility in Machine Learning Research (A Report from the NeurIPS 2019 Reproducibility Program)
• Direct Feedback Alignment Provides Learning in Deep Neural Networks
• How Auto-Encoders Could Provide Credit Assignment in Deep Networks via Target Propagation
• Torchattacks: A PyTorch Repository for Adversarial Attacks
• Random feedback weights support learning in deep neural networks
• Deep Learning without Weight Transport
• How Important is Weight Symmetry in Backpropagation?
• Feedback alignment in deep convolutional networks
• Biologically-plausible learning algorithms can scale to large datasets
• Deriving Differential Target Propagation from Iterating Approximate Inverses
• Comment on "Adv-BNN: Improved Adversarial Defense through Robust Bayesian Neural Network"
• Understanding Reuse, Performance, and Hardware Cost of DNN Dataflows: A Data-Centric Approach Using MAESTRO
• Hardware Beyond Backpropagation: a Photonic Co-Processor for Direct Feedback Alignment
• Adversarial Robustness by Design through Analog Computing and Synthetic Gradients
• On the Adversarial Robustness of Neural Networks without Weight Transport