A drive-reinforcement model of single neuron function: An alternative to the Hebbian neuronal model
AIP Conference Proceedings 151 on Neural Networks for Computing
AIP Conference Proceedings 151 on Neural Networks for Computing
Self-organization and associative memory: 3rd edition
Self-organization and associative memory: 3rd edition
Intelligence without representation
Artificial Intelligence
A new class of iterative methods for nonselfadjoint or indefinite problems
SIAM Journal on Numerical Analysis
Technical Note: \cal Q-Learning
Machine Learning
TD(λ) Converges with Probability 1
Machine Learning
Error estimates on a new nonlinear Galerkin method based on two-grid finite elements
SIAM Journal on Numerical Analysis
Digital signal processing (3rd ed.): principles, algorithms, and applications
Digital signal processing (3rd ed.): principles, algorithms, and applications
Two-grid Discretization Techniques for Linear and Nonlinear PDEs
SIAM Journal on Numerical Analysis
A Two-Level Method for the Discretization of Nonlinear Boundary Value Problems
SIAM Journal on Numerical Analysis
A Two-Grid Finite Difference Scheme for Nonlinear Parabolic Equations
SIAM Journal on Numerical Analysis
Neural Networks - Special issue on neural control and robotics: biology and technology
Local and parallel finite element algorithms based on two-grid discretizations
Mathematics of Computation
Introduction to Reinforcement Learning
Introduction to Reinforcement Learning
Digital Signal Processing: System Analysis and Design
Digital Signal Processing: System Analysis and Design
Linear Control System Analysis and Design
Linear Control System Analysis and Design
Finite Element Method for Elliptic Problems
Finite Element Method for Elliptic Problems
Learning to Predict by the Methods of Temporal Differences
Machine Learning
Isotropic sequence order learning
Neural Computation
Motor primitive and sequence self-organization in a hierarchical recurrent neural network
Neural Networks - 2004 Special issue: New developments in self-organizing systems
Temporal Difference Model Reproduces Anticipatory Neural Activity
Neural Computation
Reinforcement learning: a survey
Journal of Artificial Intelligence Research
IWINAC '07 Proceedings of the 2nd international work-conference on Nature Inspired Problem-Solving Methods in Knowledge Engineering: Interplay Between Natural and Artificial Computation, Part II
Efference copies in neural control of dynamic biped walking
Robotics and Autonomous Systems
Adaptive Sensor-Driven Neural Control for Learning in Walking Machines
ICONIP '09 Proceedings of the 16th International Conference on Neural Information Processing: Part II
Embodied evolution and learning: the neglected timing of maturation
ECAL'07 Proceedings of the 9th European conference on Advances in artificial life
A novel information measure for predictive learning in a social system setting
SAB'10 Proceedings of the 11th international conference on Simulation of adaptive behavior: from animals to animats
Extraction of reward-related feature space using correlation-based and reward-based learning methods
ICONIP'10 Proceedings of the 17th international conference on Neural information processing: theory and algorithms - Volume Part I
Formal modeling of robot behavior with learning
Neural Computation
Hi-index | 0.00 |
Currently all important, low-level, unsupervised network learning algorithms follow the paradigm of Hebb, where input and output activity are correlated to change the connection strength of a synapse. However, as a consequence, classical Hebbian learning always carries a potentially destabilizing autocorrelation term, which is due to the fact that every input is in a weighted form reflected in the neuron's output. This self-correlation can lead to positive feedback, where increasing weights will increase the output, and vice versa, which may result in divergence. This can be avoided by different strategies like weight normalization or weight saturation, which, however, can cause different problems. Consequently, in most cases, high learning rates cannot be used for Hebbian learning, leading to relatively slow convergence. Here we introduce a novel correlation-based learning rule that is related to our isotropic sequence order (ISO) learning rule (Porr & Wörgötter, 2003a), but replaces the derivative of the output in the learning rule with the derivative of the reflex input. Hence, the new rule uses input correlations only, effectively implementing strict heterosynaptic learning. This looks like a minor modification but leads to dramatically improved properties. Elimination of the output from the learning rule removes the unwanted, destabilizing autocorrelation term, allowing us to use high learning rates. As a consequence, we can mathematically show that the theoretical optimum of one-shot learning can be reached under ideal conditions with the new rule. This result is then tested against four different experimental setups, and we will show that in all of them, very few (and sometimes only one) learning experiences are needed to achieve the learning goal. As a consequence, the new learning rule is up to 100 times faster and in general more stable than ISO learning.