探索深度学习机器的函数空间
Exploring the Function Space of Deep-Learning Machines
摘要：
深度学习机器的函数空间是通过研究给定误差的函数相对于参考函数的熵的增长来研究的，由深度学习机器实现。使用物理启发的方法，我们研究稀疏和密集连接的架构，以发现候选函数的逐层收敛，其特征在于接近参考函数时熵的相应减少，深入了解具有大量层的重要性，并随着误差的增加观察相变。
英文摘要：
The function space of deep-learning machines is investigated by studying growth in the entropy of functions of a given error with respect to a reference function, realized by a deep-learning machine. Using physics-inspired methods we study both sparsely and densely-connected architectures to discover a layer-wise convergence of candidate functions, marked by a corresponding reduction in entropy when approaching the reference function, gain insight into the importance of having a large number of layers, and observe phase transitions as the error increases.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
