# Controlling Recurrent Neural Networks by Conceptors

arXiv: https://arxiv.org/abs/1403.3369 · HTML: https://mlsanity.com/paper/1403.3369/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Mar 2014.

## Built on by (most cited first, 16 of 16)

- [Steering Large Language Models using Conceptors: Improving Addition-Based Activation Engineering](https://mlsanity.com/paper/2410.16314/) (2024)
- [Initializing LSTM internal states via manifold learning](https://mlsanity.com/paper/2104.13101/) (2021)
- [Conceptor-Aided Debiasing of Large Language Models](https://mlsanity.com/paper/2211.11087/) (2022)
- [CODE-CL: Conceptor-Based Gradient Projection for Deep Continual Learning](https://mlsanity.com/paper/2411.15235/) (2024)
- [Certified Invertibility in Neural Networks via Mixed-Integer Programming](https://mlsanity.com/paper/2301.11783/) (2023)
- [Conceptors for Semantic Steering](https://mlsanity.com/paper/2605.04980/) (2026)
- [Contrastive Conceptor Activation Steering (COAST): Unlocking Vision-Language-Action Models through Hidden States](https://mlsanity.com/paper/2605.17144/) (2026)
- [Evolutionary Echo State Network: evolving reservoirs in the Fourier space](https://mlsanity.com/paper/2206.04951/) (2022)
- [Fast Classification Learning with Neural Networks and Conceptors for Speech Recognition and Car Driving Maneuvers](https://mlsanity.com/paper/2102.05588/) (2021)
- [Conceptor Learning for Class Activation Mapping](https://mlsanity.com/paper/2201.08636/) (2022)
- [Change Point Detection with Conceptors](https://mlsanity.com/paper/2308.06213/) (2023)
- [Adaptive control of recurrent neural networks using conceptors](https://mlsanity.com/paper/2405.07236/) (2024)
- [The Devil Is in Gradient Entanglement: Energy-Aware Gradient Coordinator for Robust Generalized Category Discovery](https://mlsanity.com/paper/2604.14176/) (2026)
- [Recursive Binding on a Budget: Subspace Carving in Order-p Tensor Memories](https://mlsanity.com/paper/2606.11391/) (2026)
- [Organization of computation in reservoir computing](https://mlsanity.com/paper/2607.17858/) (2026)
- [PCA-guided Activation Scaling for Monotonic Bidirectional Control over LLM Sycophancy](https://mlsanity.com/paper/2608.16650/) (2026)

## Abstract (arXiv)

The human brain is a dynamical system whose extremely complex sensor-driven neural processes give rise to conceptual, logical cognition. Understanding the interplay between nonlinear neural dynamics and concept-level cognition remains a major scientific challenge. Here I propose a mechanism of neurodynamical organization, called conceptors, which unites nonlinear dynamics with basic principles of conceptual abstraction and logic. It becomes possible to learn, store, abstract, focus, morph, generalize, de-noise and recognize a large number of dynamical patterns within a single neural system; novel patterns can be added without interfering with previously acquired ones; neural noise is automatically filtered. Conceptors help explaining how conceptual-level information processing emerges naturally and robustly in neural systems, and remove a number of roadblocks in the theory and applications of recurrent neural networks.