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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Transfer learning refers to the use of knowledge gained while solving amachine learning task and applying it to the solution of a closely relatedproblem. Such an approach has enabled scientific breakthroughs in computervision and natural language processing where the weights learned instate-of-the-art models can be used to initialize models for other tasks whichdramatically improve their performance and save computational time. Here wedemonstrate an unsupervised learning approach augmented with basic physicalprinciples that achieves fully transferrable learning for problems instatistical physics across different physical regimes. By coupling a sequencemodel based on a recurrent neural network to an extensive deep neural network,we are able to learn the equilibrium probability distributions andinter-particle interaction models of classical statistical mechanical systems.Our approach, distribution-consistent learning, DCL, is a general strategy thatworks for a variety of canonical statistical mechanical models (Ising andPotts) as well as disordered (spin-glass) interaction potentials. Using datacollected from a single set of observation conditions, DCL successfullyextrapolates across all temperatures, thermodynamic phases, and can be appliedto different length-scales. This constitutes a fully transferrablephysics-based learning in a generalizable approach.

Watch and learn -- a generalized approach for transferrable learning in deep neural networks via physical principles