IEEE Transactions on Cognitive and Developmental Systems

A path planning algorithm for outdoor robots, which is based on neuronal spike timing, is introduced. The algorithm is inspired by recent experimental evidence for experience-dependent plasticity of axonal conductance. Based on this evidence, we developed a novel learning rule that altered axonal delays corresponding to cost traversals and demonstrated its effectiveness on real-world environmental... View full abstract»

This paper presents a natural mechanism of the human brain for generating a dynamic path planning in 3-D rough terrain. The proposed paper not only emphasizes the inner state process of the neuron but also the development process of the neurons in the brain. There are two algorithm processes in this proposed model, the forward transmission activity for constructing the neuron connections to find t... View full abstract»

The brain-inspired spiking neurons, considered as the third generation of artificial neurons, are more biologically plausible and computationally powerful than traditional artificial neurons. One of the fundamental research in spiking neurons is to transform streams of incoming spikes into precisely timed spikes. Due to the inherent complexity of processing spike sequences, the formulation of effi... View full abstract»

Using the iCub humanoid robot with an artificial pressure-sensitive skin, we investigate how representations of the whole skin surface resembling those found in primate primary somatosensory cortex can be formed from local tactile stimulations traversing the body of the physical robot. We employ the well-known self-organizing map algorithm and introduce its modification that makes it possible to r... View full abstract»

Manually programming robots is difficult, impeding more widespread use of robotic systems. In response, efforts are being made to develop robots that use imitation learning. With such systems a robot learns by watching humans perform tasks. However, most imitation learning systems replicate a demonstrator's actions rather than obtaining a deeper understanding of why those actions occurred. Here we... View full abstract»

The computational model for spike train prediction with inputs from other related cerebral cortices is important in revealing the underlying connection among different cortical areas. To evaluate goodness-of-fit of the model, the time rescaling Kolmogorov-Smirnov (KS) statistic is usually applied, of which the calculation is separated from optimization procedure of the model. If the KS statistic c... View full abstract»

This paper proposes a feedforward visual pattern recognition model based on a spiking neural network (SNN). The proposed model mainly includes four functional layers: 1) feature extraction; 2) encoding; 3) learning; and 4) readout. A modified HMAX model is first presented to extract features from external stimuli. In order to reduce the computational cost, we simplify the S1 layer using a single G... View full abstract»

This paper proposes a novel approach of integrating different neuroimaging techniques to characterize an autistic brain. Different techniques like electroencephalography (EEG), functional magnetic resonance imaging (fMRI), and diffusion tensor imaging (DTI) have traditionally been used to find biomarkers for autism, but there have been very few attempts for a combined or multimodal approach of EEG... View full abstract»

Being able to learn word meanings across multiple scenes consisting of multiple words and referents (i.e., cross-situationally) is thought to be important for language acquisition. The ability has been studied in infants, children, and adults, and yet there is much debate about the basic storage and retrieval mechanisms that operate during cross-situational word learning. It has been difficult to ... View full abstract»

Neuroscientific studies suggest that the dorsal premotor area is activated by biological motions, and is also related to the prediction errors of observed and self-induced motions. We hypothesize that biological and nonbiological motions can be discriminated by such prediction errors. We therefore propose a model to verify this hypothesis. A neural network model is constructed that learns to predi... View full abstract»

Imagine a day when humans can form mental representations of higher-dimensional space and objects. These higher-dimensional spatial representations may enable us to gain unique insights into scientific and cultural advancements. To augment human spatial cognition from three to four dimensions, we have developed an interactive 4-D visualization system for acquiring an understanding of 4-D space and... View full abstract»

EEG signals (EEGs) are usually collected by placing multiple electrodes at various positions along the scalp as multichannel data. Given that many channels are collected for each single-trial, the multichannel EEG classification problem can be treated as multivariate time series classification problem. For multichannel EEG data to be more accurately classified, we propose an algorithm, called the ... View full abstract»

As a recently proposed method for subspace learning, principal coefficients embedding (PCE) method can automatically determine the dimension of the feature space and robustly handle various corruptions in real-world applications. However, the projection matrix learned by PCE is not orthogonal, so the original data may be reconstructed improperly. To address this issue, we proposed a new method ter... View full abstract»

Reinforcement learning brings flexibility and generality for machine learning, while most of them are mathematical optimization driven approaches, and lack of cognitive and neural evidence. In order to provide a more cognitive and neural mechanisms driven foundation and validate its applicability in complex task, we develop a basal ganglia (BG) network centric reinforcement learning model. Compare... View full abstract»

An integrated biologically inspired self-organizing map (SOM) algorithm is proposed for task assignment and path planning of an autonomous underwater vehicle (AUV) system in 3-D underwater environments with obstacle avoidance. The algorithm embeds the biologically inspired neural network (BINN) into the SOM neural networks. The task assignment and path planning aim to arrange a team of AUVs to vis... View full abstract»

This paper introduces new results on the modeling of early vocal development using artificial intelligent cognitive architectures and a simulated vocal tract. The problem is addressed using intrinsically motivated learning algorithms for autonomous sensorimotor exploration, a kind of algorithm belonging to the active learning architectures family. The artificial agent is able to autonomously selec... View full abstract»

Animal learning is driven not only by biological needs but also by intrinsic motivations (IMs) serving the acquisition of knowledge. Computational modeling involving IMs is indicating that learning of motor skills requires that autonomous agents self-generate tasks/goals and use them to acquire skills solving/leading to them. We propose a neural architecture driven by IMs that is able to self-gene... View full abstract»

This paper investigates how adequate coordination among the different cognitive processes of a humanoid robot can be developed through end-to-end learning of direct perception of visuomotor stream. We propose a deep dynamic neural network model built on a dynamic vision network, a motor generation network, and a higher-level network. The proposed model was designed to process and to integrate dire... View full abstract»

Storing and reproducing temporal intervals is an important component of perception, action generation, and learning. How temporal intervals can be represented in neuronal networks is thus an important research question both in study of biological organisms and artificial neuromorphic systems. Here, we introduce a neural-dynamic computing architecture for learning temporal durations of actions. The... View full abstract»

A reliable method for quantifying cognitive workload in pilots could find uses in flight training and scheduling, cockpit design, and improving flight safety. Many proposed methods for monitoring cognitive workload in this population rely on measuring physiological responses to externally delivered probe stimuli and/or use traditional gel-based electroencephalography (EEG) sensors. Here we develop... View full abstract»

Robotic hand-eye coordination is recognized as an important skill to deal with complex real environments. Conventional robotic hand-eye coordination methods merely transfer stimulus signals from robotic visual space to hand actuator space. This paper introduces a reverse method. Build another channel that transfers stimulus signals from robotic hand space to visual space. Based on the reverse chan... View full abstract»

Gait recognition, i.e., identification of an individual from his/her walking pattern is an emerging field. While existing gait recognition techniques perform satisfactorily in normal walking conditions, their performance tend to suffer drastically with variations in clothing and carrying conditions. In this paper, we propose a novel covariate cognizant framework to deal with the presence of such c... View full abstract»