Learn More
We present an efficient online learning scheme for non-negative sparse coding in autoencoder neural networks. It comprises a novel synaptic decay rule that ensures non-negative weights in combination with an intrinsic self-adaptation rule that optimizes sparseness of the non-negative encoding. We show that non-negativity constrains the space of solutions(More)
The data-driven approximation of vector fields that encode dynamical systems is a persistently hard task in machine learning. If data is sparse and given in form of velocities derived from few trajectories only, state-space regions exists, where no information on the vector field and its induced dynamics is available. Generalization towards such regions is(More)
Bionic soft robots offer exciting perspectives for more flexible and safe physical interaction with the world and humans. Unfortunately, their hardware design often prevents analytical modeling, which in turn is a prerequisite to apply classical automatic control approaches. On the other hand, also modeling by means of learning is hardly feasible due to(More)
We present a dynamical system approach to learning forward and inverse kinematics of a humanoid upper body in associative radial basis function networks. Coupling of arm kinematics via the torso joints is modeled by dynamically coupling two networks learning the direct inverse kinematics of both torso-arm chains separately. Dividing the upper body(More)
This paper proposes an efficient neural network model for learning the articulatory-acoustic forward and inverse mapping of consonant-vowel sequences including coarticulation effects. It is shown that the learned models can generalize vowels as well as consonants to other contexts and that the need for supervised training examples can be reduced by refining(More)
Simultaneous mastering of multiple tasks during motion generation is challenging. Traditional null-space based approaches for redundant robots implement a strict, hierarchical prioritization for tracking multiple objectives. In consequence, these schemes are not suited to impose smooth priorities or changing them during motion execution. A recently(More)
—We introduce a novel recurrent neural network controller that learns and maintains multiple solutions of the inverse kinematics. Redundancies are resolved dynamically by means of multi-stable attractor dynamics. The associative network comprises a combined forward and inverse model of the robot's kinematics and enables flexible selection of control spaces(More)
— We present a connectionist approach to learn forward and redundant inverse kinematics in a single recurrent network. The network architecture extends the reservoir computing idea, i.e. to read out the state of a fixed dynamic system, into an associative setting, which learns the forward and backward mapping simultaneously. For output learning we use(More)
Output feedback is crucial for autonomous and parameterized pattern generation with reservoir networks. Read-out learning affects the output feedback loop and can lead to error amplification. Regularization is therefore important for both, generalization and reduction of error amplification. We show that regularization of the reservoir and the read-out(More)
— We introduce a novel control framework based on a recurrent neural network for reaching movement generation. The network first learns forward and inverse kinematics, i.e. to associate end effector coordinates with joint angles, by means of attractor states. Modulating the attractor states with the desired target input allows generalization of the learned(More)