English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

This study proposes a novel biologically-motivated learning method for deepconvolutional neural networks (CNNs). The combination of CNNs and backpropagation (BP) learning is the most powerful method in recent machinelearning regimes. However, it requires large labeled data for training, andthis requirement can occasionally become a barrier for real world applications.To address this problem and utilize unlabeled data, I propose to introduceunsupervised competitive learning which only requires forward propagatingsignals as a pre-training method for CNNs. The method was evaluated by imagediscrimination tasks using MNIST, CIFAR-10, and ImageNet datasets, and itachieved a state-of-the-art performance as a biologically-motivated method inthe ImageNet experiment. The results suggested that the method enableshigher-level learning representations solely from forward propagating signalswithout a backward error signal for the learning of convolutional layers. Theproposed method could be useful for a variety of poorly labeled data, forexample, time series or medical data.

Biologically-Motivated Deep Learning Method using Hierarchical Competitive Learning