We present a framework for designing cheap control architectures of embodied agents. Our derivation is guided by the classical problem of universal approximation, whereby we explore the possibility of exploiting the agent's embodiment for a new and m...
IEEE transactions on neural networks and learning systems
Aug 28, 2015
In this brief, the asymptotic stability properties of a neutral delay neuron system are studied mainly in a critical case when the exponential stability is not possible. If a critical value of the coefficient in the neutral delay neuron system is con...
In recent years there has been a growing interest in the field of dynamic walking and bio-inspired robots. However, while walking and running on a flat surface have been studied extensively, walking dynamically over terrains with varying slope remain...
Motivated by neuroscience discoveries during the last few years, many studies consider pulse-coupled neural networks with spike-timing as an essential component in information processing by the brain. There also exists some technical challenges while...
Neural networks : the official journal of the International Neural Network Society
Aug 18, 2015
The application of biologically inspired methods in design and control has a long tradition in robotics. Unlike previous approaches in this direction, the emerging field of neurorobotics not only mimics biological mechanisms at a relatively high leve...
IEEE transactions on neural networks and learning systems
Aug 7, 2015
This paper studies both indirect and direct global neural control of strict-feedback systems in the presence of unknown dynamics, using the dynamic surface control (DSC) technique in a novel manner. A new switching mechanism is designed to combine an...
Synaptic (phasic) lateral inhibition between neuronal columns mediated by GABAergic interneurons is, in general, essential for primary sensory cortices to respond selectively to elemental features. We propose here a neural network model with a nonsyn...
Neural networks : the official journal of the International Neural Network Society
Jul 15, 2015
Semi-supervised learning (SSL) is a typical learning paradigms training a model from both labeled and unlabeled data. The traditional SSL models usually assume unlabeled data are relevant to the labeled data, i.e., following the same distributions of...
OBJECTIVE: Brain-computer interfaces (BCIs) represent a technology with the potential to rehabilitate a range of traumatic and degenerative nervous system conditions but require a time-consuming training process to calibrate. An area of BCI research ...
Many neurodegenerative diseases arise from the malfunctioning neurons in the pathway where the signal is carried. In this paper, we propose neuron specific TDMA/multiplexing and demultiplexing mechanisms to convey the spikes of a receptor neuron over...