arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1606.08808cs.LGcs.AI
收藏

数据随机映射的自适应训练Quantization

Adaptive Training of Random Mapping for Data Quantization

Qingdao University(青岛大学);Macau University of Science and Technology(澳门科技大学)

Miao Cheng, Ah Chung Tsoi

摘要:

数据量化学习具有特定要求的数据的编码结果,并为数据处理的许多实际应用提供了广阔的前景。然而,编码器的结果通常限于随机映射的多变量输入,并且二进制码的边信息很难尽可能地描述原始数据模式。在文献中,基于余弦的随机量化由于其固有的有界结果而引起了广泛的关注。然而,它通常遭受不确定的输出,和原始数据的信息不能完全保留在减少码。在这项工作中,一种新的二进制嵌入方法,称为自适应训练量化(ATQ),提出了学习随机编码器的理想变换,其中余弦随机映射的限制得到解决。作为一种自适应学习思想,利用数据组的思想自适应地计算约简映射,同时改进随机变换的偏差,以保持最多的匹配信息。实验结果表明,与其他随机量化方法相比,该方法能够获得优异的性能。

英文摘要:

Data quantization learns encoding results of data with certain requirements, and provides a broad perspective of many real-world applications to data handling. Nevertheless, the results of encoder is usually limited to multivariate inputs with the random mapping, and side information of binary codes are hardly to mostly depict the original data patterns as possible. In the literature, cosine based random quantization has attracted much attentions due to its intrinsic bounded results. Nevertheless, it usually suffers from the uncertain outputs, and information of original data fails to be fully preserved in the reduced codes. In this work, a novel binary embedding method, termed adaptive training quantization (ATQ), is proposed to learn the ideal transform of random encoder, where the limitation of cosine random mapping is tackled. As an adaptive learning idea, the reduced mapping is adaptively calculated with idea of data group, while the bias of random transform is to be improved to hold most matching information. Experimental results show that the proposed method is able to obtain outstanding performance compared with other random quantization methods.

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。

↑