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

Recent studies have demonstrated that the performance of transformers on thetask of language modeling obeys a power-law relationship with model size oversix orders of magnitude. While transformers exhibit impressive scaling, theirperformance hinges on processing large amounts of data, and their computationaland memory requirements grow quadratically with sequence length. Motivated bythese considerations, we construct a Legendre Memory Unit based model thatintroduces a general prior for sequence processing and exhibits an $O(n)$ and$O(n \ln n)$ (or better) dependency for memory and computation respectively.Over three orders of magnitude, we show that our new architecture attains thesame accuracy as transformers with 10x fewer tokens. We also show that for thesame amount of training our model improves the loss over transformers about asmuch as transformers improve over LSTMs. Additionally, we demonstrate thatadding global self-attention complements our architecture and the augmentedmodel improves performance even further.

Language Modeling using LMUs: 10x Better Data Efficiency or Improved Scaling Compared to Transformers