arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2209.00525cs.LGcs.AI
收藏

深度学习中表示的复杂性

Complexity of Representations in Deep Learning

IBM Watson Health(IBM沃森健康)

Tin Kam Ho

摘要:

深度神经网络使用多层函数来将由输入向量表示的对象逐步映射到不同的表示,并且经过充分的训练,最终映射到作为最终决策函数输出的每个类的单个分数。理想情况下,在这个输出空间中,不同类的对象实现了最大程度的分离。出于更好地理解深层神经网络内部工作的需要,我们从数据复杂性的角度分析了学习表示在分离类方面的有效性。使用一个简单的复杂性度量,一个流行的基准测试任务和一个著名的架构设计,我们展示了数据复杂性如何在网络中演变,它在训练过程中如何变化,以及它如何受到网络设计和训练样本可用性的影响。我们讨论的意见和进一步研究的潜力的影响。

英文摘要:

Deep neural networks use multiple layers of functions to map an object represented by an input vector progressively to different representations, and with sufficient training, eventually to a single score for each class that is the output of the final decision function. Ideally, in this output space, the objects of different classes achieve maximum separation. Motivated by the need to better understand the inner working of a deep neural network, we analyze the effectiveness of the learned representations in separating the classes from a data complexity perspective. Using a simple complexity measure, a popular benchmarking task, and a well-known architecture design, we show how the data complexity evolves through the network, how it changes during training, and how it is impacted by the network design and the availability of training samples. We discuss the implications of the observations and the potentials for further studies.

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。

↑