The backpropagation algorithm has long been the canonical training method for neural networks. Modern paradigms are implicitly optimized for it, and numerous guidelines exist to ensure its proper use. Recently, synthetic gradients methods -where the error gradient is only roughly approximated - have garnered interest. These methods not only better portray how biological brains are learning, but also open new computational possibilities, such as updating layers asynchronously. Even so, they have failed to scale past simple tasks like MNIST or CIFAR-10. This is in part due to a lack of standards, leading to ill-suited models and practices forbidding such methods from performing to the best of their abilities. In this work, we focus on direct feedback alignment and present a set of best practices justified by observations of the alignment angles. We characterize a bottleneck effect that prevents alignment in narrow layers, and hypothesize it may explain why feedback alignment methods have yet to scale to large convolutional networks.
正在进行的研究已经确定了生物网络和深度人工神经网络中神经表征之间的相似性。这使得人们对开发用于训练人工网络的反向传播学习算法与大脑中的突触可塑性规则之间的类比重新产生了兴趣。这些努力受到反向传播的生物学上难以置信的特征的挑战，其中之一是对对称的前向和后向突触权重的依赖。已经提出了许多不依赖于权重对称的方法，但到目前为止，这些方法未能扩展到深度卷积网络和复杂数据。我们确定的主要障碍，这种算法的可扩展性，并介绍了几种技术来减轻它们。我们证明，修改后的反馈对齐方法，强制执行较弱形式的权重对称性，一个需要协议的重量符号，但不幅度，可以实现与反向传播的性能竞争。我们的研究结果补充了Bartunov et al.（2018）和Xiao et al.（2018 b）的研究结果，并表明促进前馈和反馈权重对齐的机制对于深度网络中的学习至关重要。
Align, then memorise: the dynamics of learning with feedback alignment
Ecole Normale Supérieure（巴黎高等师范学院）；EPFL（洛桑联邦理工学院）；Facebook AI Research（脸书人工智能研究院）；LightOn；International School of Advanced Studies (SISSA)（国际高等研究学院（SISSA））
A Statistical Framework for Alignment with Biased AI Feedback
Center for Data Science, Zhejiang University（浙江大学数据科学中心）；Department of Electrical and Computer Engineering, Rutgers University（罗格斯大学电气与计算机工程系）；Department of Statistics, Rutgers University（罗格斯大学统计学系）；Faculty of Business and Economics, The University of Hong Kong（香港大学商学院）
Scalable Valuation of Human Feedback through Provably Robust Model Alignment
The University of Osaka（大阪大学）；Lattice Lab, Toyota Motor Corporation（丰田公司Lattice实验室）；Machine Learning Research Group, University of Oxford（牛津大学机器学习研究组）；RIKEN AIP（理化学研究所AIP）
