Architecture Augmentation for Performance Predictor via Graph Isomorphism.

Neural architecture search (NAS) can automatically design architectures for deep neural networks (DNNs) and has become one of the hottest research topics in the current machine learning community. However, NAS is often computationally expensive because a large number of DNNs require to be trained for obtaining performance during the search process. Performance predictors can greatly alleviate the prohibitive cost of NAS by directly predicting the performance of DNNs. However, building satisfactory performance predictors highly depends on enough trained DNN architectures, which are difficult to obtain due to the high computational cost. To solve this critical issue, we propose an effective DNN architecture augmentation method named graph isomorphism-based architecture augmentation method (GIAug) in this article. Specifically, we first propose a mechanism based on graph isomorphism, which has the merit of efficiently generating a factorial of n (i.e., n ) diverse annotated architectures upon a single architecture having n nodes. In addition, we also design a generic method to encode the architectures into the form suitable to most prediction models. As a result, GIAug can be flexibly utilized by various existing performance predictors-based NAS algorithms. We perform extensive experiments on CIFAR-10 and ImageNet benchmark datasets on small-, medium- and large-scale search space. The experiments show that GIAug can significantly enhance the performance of the state-of-the-art peer predictors. In addition, GIAug can save three magnitude order of computation cost at most on ImageNet yet with similar performance when compared with state-of-the-art NAS algorithms.

The enhancement and mechanism of the perception of saltiness by umami peptide from Ruditapes philippinarum and ham.

To explore the saltiness enhancement effect and mechanism of umami peptides, umami peptides from Ruditapes philippinarum and ham were mixed with NaCl and determined using electronic tongue, sensory evaluation, and the aroma chicken model (ACM), then transmembrane channel-like protein 4(TMC4) receptor was constructed for molecular docking. The results showed that KEMQKN, NGKET, RGEPNND, AHSVRFY, LSERYP, NRTF, TYLPVH, EV, AGAGPTP, and GPAGPAGPR had saltiness enhancement effect, which could be increased to 0.4-0.6 % NaCl salty taste in 0.3 % NaCl. Under neutral conditions (pH6.5), most umami peptides were in negative ion state which may be the main reason that umami peptides could bind to the TMC4 receptor and enhance saltiness. The lowest docking energy was -113.325 kcal/mol among 10 peptides and the active sites Lys568, Trp145, Tyr565, Arg151, and Gln155 in TMC4 may play a key role. Thus, this study provides basic theory and data for salt-reduction strategies.