The main goal of this work is to improve the efficiency of training binary
neural networks, which are low latency and low energy networks. The main
contribution of this work is the proposal of two solutions comprised of
topology changes and strategy training that allow the network to achieve near
the state-of-the-art performance and efficient training. The time required for
training and the memory required in the process are two factors that contribute
to efficient training.

本研究旨在提高二进制神经网络的训练效率，通过拓扑变化和策略训练提出两种解决方案，使网络能够达到接近最先进性能和高效训练。训练时间和内存需求是实现高效训练的两个因素。

无需浮点精度训练二值神经网络

Training binary neural networks without floating point precision

We present a method to match three dimensional shapes under non-isometric
deformations, topology changes and partiality. We formulate the problem as
matching between a set of pair-wise and point-wise descriptors, imposing a
continuity prior on the mapping, and propose a projected descent optimization
procedure inspired by difference of convex functions (DC) programming.
Surprisingly, in spite of the highly non-convex nature of the resulting
quadratic assignment problem, our method converges to a semantically meaningful
and continuous mapping in most of our experiments, and scales well. We provide
preliminary theoretical analysis and several interpretations of the method.

本文提出了一种通过描述符匹配、连续性限制和 DC 编程来解决三维形状匹配问题的方法，该方法可以在处理非等距变形、拓扑变化和不完整数据的情况下，有效地收敛到一种有意义的连续匹配方案，具有较好的可扩展性。