paper-with-me

Papers

Conceptors: an easy introduction

2014-06-10 · Herbert Jaeger

Conceptors provide an elementary neuro-computational mechanism which sheds a fresh and unifying light on a diversity of cognitive phenomena. A number of demanding learning and processing tasks can be solved with unprecedented ease, robustness and accuracy. Some of these tasks were impossible to solve before. This entirely informal paper introduces the basic principles of conceptors and highlights some of their usages.

📄 PDF Abstract BibTeX arXiv:1406.2671

Code (0)

등록된 구현이 없습니다.

Tasks

Diversity

Similar Papers 제목 키워드 기반

Controlling Recurrent Neural Networks by Diagonal Conceptors

2021-07-16 · J. P. de Jong

The human brain is capable of learning, memorizing, and regenerating a panoply of temporal patterns. A neuro-dynamical mechanism called conceptors offers a method for controlling the dynamics of a recurrent neural networ…

Steering Large Language Models using Conceptors: Improving Addition-Based Activation Engineering

2024-10-09 · Joris Postmus, Steven Abreu

Large language models have transformed AI, yet reliably controlling their outputs remains a challenge. This paper explores activation engineering, where outputs of pre-trained LLMs are controlled by manipulating their ac…

In-Context Learning

Overcoming Catastrophic Interference by Conceptors

2017-07-16 · Xu He, Herbert Jaeger

Catastrophic interference has been a major roadblock in the research of continual learning. Here we propose a variant of the back-propagation algorithm, "conceptor-aided back-prop" (CAB), in which gradients are shielded …

Continual Learning

Transfer between long-term and short-term memory using Conceptors

2020-03-11 · Anthony Strock, Nicolas Rougier, Xavier Hinaut

We introduce a recurrent neural network model of working memory combining short-term and long-term components. e short-term component is modelled using a gated reservoir model that is trained to hold a value from an inpu…

Conceptors for Semantic Steering

2026-05-06 · Ilias Triantafyllopoulos, Young-Min Cho, Ren Tao, Miranda Muqing Miao 외 arxiv

Activation-based steering provides control of LLM behavior at inference time, but the dominant paradigm reduces each concept to a single direction whose geometry is left largely unexamined. Rather than selecting a single…