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

We propose incremental (re)training of a neural network model to cope with acontinuous flow of new data in inference during model serving. As such, this isa life-long learning process. We address two challenges of life-longretraining: catastrophic forgetting and efficient retraining. If we combine allpast and new data it can easily become intractable to retrain the neuralnetwork model. On the other hand, if the model is retrained using only newdata, it can easily suffer catastrophic forgetting and thus it is paramount tostrike the right balance. Moreover, if we retrain all weights of the modelevery time new data is collected, retraining tends to require too manycomputing resources. To solve these two issues, we propose a novel retrainingmodel that can select important samples and important weights utilizingmulti-armed bandits. To further address forgetting, we propose a newregularization term focusing on synapse and neuron importance. We analyzemultiple datasets to document the outcome of the proposed retraining methods.Various experiments demonstrate that our retraining methodologies mitigate thecatastrophic forgetting problem while boosting model performance.

Neural Network Retraining for Model Serving