Echo state networks (ESNs) are a powerful form of reservoir computing that only require training linear output weights whilst the internal is formed fixed randomly connected neurons. With correctly scaled connectivity matrix, neurons' activity exhibits echo-state property and responds to input dynamics with certain timescales. Tuning timescales network can be necessary for treating tasks, some ...

Dependency parsing is a crucial step towards deep language understanding and, therefore, widely demanded by numerous Natural Language Processing applications. In particular, left-to-right and top-down transition-based algorithms that rely on Pointer Networks are among the most accurate approaches for performing dependency parsing. Additionally, it has been observed algorithm Networks’ sequentia...