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 Tools annual

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 monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Learning from the data stored in a database is an important functionincreasingly available in relational engines. Methods using lower precisioninput data are of special interest given their overall higher efficiency but,in databases, these methods have a hidden cost: the quantization of the realvalue into a smaller number is an expensive step. To address the issue, in thispaper we present MLWeaving, a data structure and hardware accelerationtechnique intended to speed up learning of generalized linear models indatabases. ML-Weaving provides a compact, in-memory representation enabling theretrieval of data at any level of precision. MLWeaving also takes advantage ofthe increasing availability of FPGA-based accelerators to provide a highlyefficient implementation of stochastic gradient descent. The solution adoptedin MLWeaving is more efficient than existing designs in terms of space (sinceit can process any resolution on the same design) and resources (via the use ofbit-serial multipliers). MLWeaving also enables the runtime tuning ofprecision, instead of a fixed precision level during the training. Weillustrate this using a simple, dynamic precision schedule. Experimentalresults show MLWeaving achieves up to16 performance improvement overlow-precision CPU implementations of first-order methods.

Accelerating Generalized Linear Models with MLWeaving: A One-Size-Fits-All System for Any-precision Learning (Technical Report)