Controlling Recurrent Neural Networks by Conceptors
arXiv:1403.3369
Abstract
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.
200 pages, 50 figures
References in corpus (1)
Cited by in corpus (24)
- Artificial Neural Networks-Based Machine Learning for Wireless Networks: A Tutorial
- Dynamical learning of dynamics
- Meta Continual Learning
- Analysing Soccer Games with Clustering and Conceptors
- Conceptors: an easy introduction
- Sensorimotor Input as a Language Generalisation Tool: A Neurorobotics Model for Generation and Generalisation of Noun-Verb Combinations with Sensorimotor Inputs
- Overcoming Catastrophic Interference by Conceptors
- Reservoir Computing using Cellular Automata
- Connectionist-Symbolic Machine Intelligence using Cellular Automata based Reservoir-Hyperdimensional Computing
- Dimensions of Timescales in Neuromorphic Computing Systems
- Generalize Symbolic Knowledge With Neural Rule Engine
- Reservoir Computing for Detection of Steady State in Performance Tests of Compressors
- From statistical inference to a differential learning rule for stochastic neural networks
- Continual Learning for Sentence Representations Using Conceptors
- Initializing LSTM internal states via manifold learning
- A journey in ESN and LSTM visualisations on a language task
- Classify Images with Conceptor Network
- Unsupervised Post-processing of Word Vectors via Conceptor Negation
- Mobility-Aware Seamless Handover with MPTCP in Software-Defined HetNets
- Dynamical Phases and Resonance Phenomena in Information-Processing Recurrent Neural Networks
- Recognizing Human Internal States: A Conceptor-Based Approach
- Transfer between long-term and short-term memory using Conceptors
- Caching in the Sky: Proactive Deployment of Cache-Enabled Unmanned Aerial Vehicles for Optimized Quality-of-Experience
- Controlling Recurrent Neural Networks by Diagonal Conceptors