论文标题
什么是模棱两可的神经网络？
What is an equivariant neural network?
论文作者
论文摘要
我们解释了均等神经网络，这是机器学习中从深度卷积神经网络中进行计算机视觉的基础突破性的概念，可用于蛋白质结构预测的Alphafold 2，而无需假设对均衡性或神经网络的知识。基本的数学思想很简单，但经常被实际实现带来的工程并发症所掩盖。我们提取并专注于数学方面，并将自己限制在最终对工程问题的粗略处理中。
We explain equivariant neural networks, a notion underlying breakthroughs in machine learning from deep convolutional neural networks for computer vision to AlphaFold 2 for protein structure prediction, without assuming knowledge of equivariance or neural networks. The basic mathematical ideas are simple but are often obscured by engineering complications that come with practical realizations. We extract and focus on the mathematical aspects, and limit ourselves to a cursory treatment of the engineering issues at the end.
