Evolving Neural Update Rules for Sequence Learning
We consider the problem of searching, end to end, for effective weight and activation update rules governing online learning of a recurrent network on problems of character sequence memorisation and prediction. We experiment with a number of functional forms and find that the performance depends on them significantly. We find update rules that allow us to scale to a much larger number of recurrent units and much longer sequence lengths than has been achieved with this approach previously. We also find that natural evolution strategies significantly outperforms meta-gradients on this problem, aligning with previous studies suggesting that such evolutionary strategies are more robust than gradient back-propagation over sequences with thousands(s) of steps.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
The Past Is Prologue: A Plug-in Controller for Selective Updates in Sequentially Evolving LLM Memory
Sequentially evolving LLM memory enables agents to reuse past experience, but existing systems usually deploy each locally generated memory update without checking whether it improves future behavior. As a result, update…
Joint Learning of Experiential Rules and Policies for Large Language Model Agents
For LLM agents in multi-step interactive environments, a key challenge is to make effective use of accumulated interaction experience. Existing work has typically separated two uses of such experience: keeping it outside…
GUIDE: Guided Updates for In-context Decision Evolution in LLM-Driven Spacecraft Operations
Large language models (LLMs) have been proposed as supervisory agents for spacecraft operations, but existing approaches rely on static prompting and do not improve across repeated executions. We introduce \textsc{GUIDE}…
A new Takagi–Sugeno–Kang model for time series forecasting
A fuzzy inference system consists of a machine learning concept that combines accuracy and interpretability. They are divided into two main groups: Mamdani and Takagi–Sugeno-Kang. While Mamdani models favor interpretabil…
Time SeriesTime Series ForecastingMining Rules Incrementally over Large Knowledge Bases
Multiple web-scale Knowledge Bases, e.g., Freebase, YAGO, NELL, have been constructed using semi-supervised or unsupervised information extraction techniques and many of them, despite their large sizes, are continuously …