FP-nets as novel deep networks inspired by vision

AbstractRecently, tensor ring networks (TRNs) have been applied in deep networks, achieving remarkable successes in compression ratio and accuracy. Although highly related to the performance of TRNs, rank selection is seldom studied in previous works and usually set to equal in experiments. Meanwhile, there is not any heuristic method to choose the rank, and an enumerating way to find appropriate rank is extremely time-consuming. Interestingly, we discover that part of the rank elements is sensitive and usually aggregate in a narrow region, namely an interest region. Therefore, based on the above phenomenon, we propose a novel progressive genetic algorithm named progressively searching tensor ring network search (PSTRN), which has the ability to find optimal rank precisely and efficiently. Through the evolutionary phase and progressive phase, PSTRN can converge to the interest region quickly and harvest good performance. Experimental results show that PSTRN can significantly reduce the complexity of seeking rank, compared with the enumerating method. Furthermore, our method is validated on public benchmarks like MNIST, CIFAR10/100, UCF11 and HMDB51, achieving the state-of-the-art performance.

Download Full-text

Structure injected weight normalization for training deep networks

Multimedia Systems ◽

10.1007/s00530-021-00793-7 ◽

2021 ◽

Author(s):

Xu Yuan ◽

Xiangjun Shen ◽

Sumet Mehta ◽

Teng Li ◽

Shiming Ge ◽

...

Keyword(s):

Deep Networks

Download Full-text

Data Independent Acquisition Based Bi-Directional Deep Networks for Biometric ECG Authentication

Applied Sciences ◽

10.3390/app11031125 ◽

2021 ◽

Vol 11 (3) ◽

pp. 1125

Author(s):

Htet Myet Lynn ◽

Pankoo Kim ◽

Sung Bum Pan

Keyword(s):

Short Term Memory ◽

Feature Learning ◽

Biometric Authentication ◽

Qrs Complex ◽

Data Types ◽

Ecg Signals ◽

Data Independent Acquisition ◽

Deep Networks ◽

Classification Tasks ◽

Electrocardiogram Ecg

In this report, the study of non-fiducial based approaches for Electrocardiogram(ECG) biometric authentication is examined, and several excessive techniques are proposed to perform comparative experiments for evaluating the best possible approach for all the classification tasks. Non-fiducial methods are designed to extract the discriminative information of a signal without annotating fiducial points. However, this process requires peak detection to identify a heartbeat signal. Based on recent studies that usually rely on heartbeat segmentation, QRS detection is required, and the process can be complicated for ECG signals for which the QRS complex is absent. Thus, many studies only conduct biometric authentication tasks on ECG signals with QRS complexes, and are hindered by similar limitations. To overcome this issue, we proposed a data-independent acquisition method to facilitate highly generalizable signal processing and feature learning processes. This is achieved by enhancing random segmentation to avoid complicated fiducial feature extraction, along with auto-correlation to eliminate the phase difference due to random segmentation. Subsequently, a bidirectional recurrent neural network (RNN) with long short-term memory (LSTM) deep networks is utilized to automatically learn the features associated with the signal and to perform an authentication task. The experimental results suggest that the proposed data-independent approach using a BLSTM network achieves a relatively high classification accuracy for every dataset relative to the compared techniques. Moreover, it exhibited a significantly higher accuracy rate in experiments using ECG signals without the QRS complex. The results also revealed that data-dependent methods can only perform well for specified data types and amendments of data variations, whereas the presented approach can also be considered for generalization to other quasi-periodical biometric signal-based classification tasks in future studies.

Download Full-text