malteschilling's repositories
temporalConvolutionalNetwork
Implementation of a Temporal Convolutional Network in Keras - it is tested on a classification and regression task.
hierarchicalQuaternionMMC
Implementation of a hierarchical Mean of Multiple Computation neural network in Python. The body model is based on an axis-angle representation of joint movements using dual quaternions. It is shown in detail how the network provides a solution for the forward kinematic problem applied for the case of a seven degrees of freedom robot manipulator. Furthermore, it is used in a complex scenario of a bimanual movement task. This demonstrates how the MMC approach can be easily scaled up from a representation of a single arm to a complex model of a complete body.
AdvancedML
Course on advanced Machine Learning. (html) Slides for the lecture.
cognitiveWalker
Cognitive system for the control of a hexapod robot.
drl_seminar
Deep Reinforcement Learning Course 2017 - includes basic python implementations of (deep) reinforcement learning algorithm.
joint_mappings_nn
Learning of a mapping between different legs - given as joint angles from one (target) leg and corresponding joint angles for the posterior leg (aiming at this position).
LearningPredictiveEncoderDecoder
Learning Predictive Encoder-Decoder for falling Object images.
normalizationMMC
Implementation of a functional internal body model that is based on the Mean of Multiple Computation principle in Python. The model is completely realized in a recurrent neural network as necessary normalization steps are integrated into the neural model itself. Furthermore, a dynamic extension is applied to the model.
robust_ddrl
Experiments on Robustness of Decentralized DRL approach wrt. variation of hyper parameters of Neural Networks.