Search

This paper proposes a distributed intelligent secondary control (SC) approach based on brain emotional learning-based intelligent controller (BELBIC) for power electronic-based ac microgrid (MG). The BELBIC controller is able to learn quick-auto and handle model complexity, non-linearity, and uncertainty of the MG. The proposed controller is fully model-free, indicating that the voltage amplitude and frequency deviations are regulated without previous knowledge of the system model and parameters. This approach ensures low steady-state variations with higher bandwidth and maintains accurate power-sharing of the droop mechanism. Furthermore, primary control is realized with a robust finite control set-model predictive control (FCS-MPC) in the inner level to increase the system frequency bandwidth and a droop control in the outer level to regulate the power-sharing among the distributed generations. Finally, experimental tests obtained from a hardware-in-the-loop testbed validate the proposed control strategy for different cases.

Brain-Computer Interface (BCI) has become an established technology to interconnect a human brain and an external device. One of the most popular protocols for BCI is based on the extraction of the so-called P300 wave from electroencephalography (EEG) recordings. P300 wave is an event-related potential with a latency of 300 ms after the onset of a rare stimulus. In this paper, we used deep learning architectures, namely convolutional neural networks (CNNs), to improve P300-based BCIs. We propose a novel BCI classifier, called P3CNET, that improved P300 classification accuracy performances of the best state-of-the-art classifier. In addition, we explored pre-processing and training choices that improved the usability of BCI systems. For the pre-processing of EEG data, we explored the optimal signal interval that would improve classification accuracies. Then, we explored the minimum number of calibration sessions to balance higher accuracy and shorter calibration time. To improve the explainability of deep learning architectures, we analyzed the saliency maps of the input EEG signal leading to a correct P300 classification, and we observed that the elimination of less informative electrode channels from the data did not result in better accuracy. All the methodologies and explorations were performed and validated on two different CNN classifiers, demonstrating the generalizability of the obtained results. Finally, we showed the advantages given by transfer learning when using the proposed novel architecture on other P300 datasets. The presented architectures and practical suggestions can be used by BCI practitioners to improve its effectiveness.

Dysconnectivity of large-scale brain networks has been linked to major depression disorder (MDD) during resting state. Recent researches show that the temporal evolution of brain networks regulated by oscillations reveals novel mechanisms and neural characteristics of MDD. Our study applied a novel coupled tensor decomposition model to investigate the dysconnectivity networks characterized by spatio-temporal-spectral modes of covariation in MDD using resting electroencephalography. The phase lag index is used to calculate the functional connectivity within each time window at each frequency bin. Then, two adjacency tensors with the dimension of time frequency connectivity subject are constructed for the healthy group and the major depression group. We assume that the two groups share the same features for group similarity and retain individual characteristics for group differences. Considering that the constructed tensors are nonnegative and the components in spectral and adjacency modes are partially consistent among the two groups, we formulate a double-coupled nonnegative tensor decomposition model. To reduce computational complexity, we introduce the lowrank approximation. Then, the fast hierarchical alternative least squares algorithm is applied for model optimization. After clustering analysis, we summarize four oscillatory networks characterizing the healthy group and four oscillatory networks characterizing the major depression group, respectively. The proposed model may reveal novel mechanisms of pathoconnectomics in MDD during rest, and it can be easily extended to other psychiatric disorders. peerReviewed

Techniques for monitoring human performance traditionally rely on subjective responses and task-specific scoring, yet research suggests EEG could offer multiple performance metrics with high temporal resolution and accuracy that could be leveraged for human–computer interaction purposes. The objective of the presented work is to investigate which EEG responses correlate with task performance and evaluate whether combinations of these produce effective predictive models, facilitating further understanding of the psychological link to performance. A user study was conducted with 32 participants required to negotiate a driving course with the ambition of learning and improving ability on the course during an EEG recording session. EEG was filtered and post-processed to find power spectral density in alpha (α), beta (β), delta (δ), and theta (θ) frequency bands, as well as frontal alpha asymmetry (FAA). The initial laps were considered a baseline and an average performance improvement was calculated over the remaining laps in terms of percentage improvement in duration of track traversal. Results demonstrate event related desynchronization with increased task performance in the alpha (p =. 000), delta (p =. 000), and theta (p =. 000) bands, as well as evidence of a relationship between overall change in FAA and task efficiency. A full electrode analysis identifies δF4 as the optimal for predicting collisions, with efficiency best predicted by a combination of βOz and δF4 .

Alzheimers disease is one of the most fastest growing and costly diseases in the world today. It affects the livelihood of not just patients, but those who take care of them, including care givers, nurses, and close family members. Current progression monitoring techniques are based on scans from MRI and PET, which can be inconvenient for patients to use. In addition, more intelligent and efficient methods are needed in order to provide predictions on what the current stage of the disease is and strategies on how to slow down its progress over time. Machine learning has been around for several decades and has recently been making important contributions in medical applications. While machine learning methods have been utilised for diagnosing Alzheimers disease, they focus on using image data from MRI and PET scans, which can be difficult for patients to obtain. In this paper, machine learning was used with RF data captured from 9 different head models showing different stages of Alzheimers disease. The RF data was processed in several machine learning algorithms. Each machine learning models prediction and accuracy was generated and the results were compared to determine which machine algorithm could be used to classify different stages of Alzheimers disease using RF data that was obtained noninvasively. Results from the study showed that overall the logistic regression model had the best accuracy of 98.97% and efficiency in differentiating between 4 different stages of Alzheimers dise

In this paper we deal with a simplified anisotropic rat head phantom development and the investigation of the influence of the anisotropic white matter on electroencephalogram source localization. The proposed phantom is based on the cubic cross cell composition combined with agar mixture to set desired electrical conductivity anisotropic ratio. For the fabrication of the phantom, the 3D printed technology is exploited. Starting from a real rat brain, we proposed a simplified brain model incorporating the actual dimensions, shape and conductivity parameters of both grey and white matter containing simultaneously relevant deep-brain electrical signal sources. Five testing dipoles were located in the areas corresponding to the active brain regions. A single dipole localization error was calculated by comparing an inverse solution with a dipole position obtained from a computer tomography image. Neglecting anisotropy had a rather weak effect on localization error of a single testing dipole in our model. The reliability map was computed and interpreted in terms of spatial similarity between distributed inverse solutions involving isotropic and anisotropic forward models. We found spatially specific error increases located close to the electrodes and in the vicinity of anisotropic compartment. Hence, areas to be most sensitive to neglecting anisotropy in our model were identified.

Speech feature extraction is critical for ASR systems. Such successful features as MFCC and PLP use filterbank techniques to model log-scaled speech perception but fail to model the adaptation of human speech perception by hearing experiences. Infant perception that is adapted by hearing speech without text may cause permanent brain state modifications (engrams) that serve as a physical fundamental basis for lifetime speech perception formation. This realization motivates us to propose to model such an unsupervised adaptation process, where adaptation denotes perception that is affected or changed by the history of experiences, with the Dirichlet Process Gaussian Mixture Model (DPGMM) and the DPGMM-RNN hybrid model to extract perceptual features to improve ASR. Our proposed features extend MFCC features with posteriorgrams extracted from the DPGMM algorithm or the DPGMM-RNN hybrid model. Our analysis shows that the DPGMM and DPGMM-RNN model perplexities agree with infant auditory perplexity to support that the proposed features are perceptual. Our ASR results verify the effectiveness of the proposed unsupervised features in such tasks as LVCSR on WSJ and ASR on noisy low-resource telephone conversations, compared with the supervised bottleneck features from Kaldi in ASR performance.

Publisher Copyright: Author The human brain can be described as a complex network of functional connections between distinct regions, referred to as the brain functional network. Recent studies show that the functional network is a dynamic process and its community structure evolves with time during continuous task performance. Consequently, it is important for the understanding of the human brain to develop dynamic community detection techniques for such time-varying functional networks. Here, we propose a temporal clustering framework based on a set of network generative models and surprisingly it can be linked to Block Component Analysis to detect and track the latent community structure in dynamic functional networks. Specifically, the temporal dynamic networks are represented within a unified three-way tensor framework for simultaneously capturing multiple types of relationships between a set of entities. The multi-linear rank-(Lr,Lr,1) block term decomposition (BTD) is adopted to fit the network generative model to directly recover underlying community structures with the specific evolution of time from the temporal networks. We apply the proposed method to the study of the reorganization of the dynamic brain networks from electroencephalography (EEG) data recorded during free music listening. We derive several network structures (Lr communities in each component) with specific temporal patterns (described by BTD components) significantly modulated by musical features, involving subnetworks of frontoparietal, default mode, and sensory-motor networks. The results show that the brain functional network structures are dynamically reorganized and the derived community structures are temporally modulated by the music features. The proposed generative modeling approach can be an effective tool for describing community structures in brain networks that go beyond static methods and detecting the dynamic reconfiguration of modular connectivity elicited by continuously naturalistic tasks.

This review article discusses the definition and implementation of brain–computer interface (BCI) system relying on brain connectivity (BC) and machine learning/deep learning (DL) for motor imagery (MI)-based applications. During the past few years, many approaches have been explored in terms of types of neurological sources of information, feature extraction, and intention prediction for BCI applications. Two novel aspects are becoming increasingly interesting for the BCI community: BC modeling and DL. The former aims at describing the interactions among different brain regions as connectivity patterns that reflect the dynamics of information flow either at rest or when performing a task. The latter is becoming pervasive for its capability of modeling and predicting complex data, where a huge amount of information is involved. In this scenario, we conducted a systematic literature review on BCI studies that led to the selection of 34 articles meeting all the required criteria. This provides evidence of the rapid growth of the topic over the past few years, though being still in its infancy. The last part of this article is dedicated to this new frontier of BCI that we call MI BC-based computer interfaces highlighting the potential of BC features. This, jointly with DL as enabling technology, has the potential of improving the performance of electroencephalography-based systems.

Emotion regulation to pleasant and unpleasant stimuli involves several brain areas, such as the prefrontal cortex, amygdala, and insular cortex. However, how a specific arousal level affects such brain dynamics is not fully understood. To this effect, we propose an electroencephalography (EEG)-based study, where 22 healthy subjects were emotionally elicited through affective pictures gathered from the International Affective Picture System. Based on the circumplex model of affect, we used four arousing levels, each with two valence levels (i.e., pleasant and unpleasant). Considering these levels, we investigated the EEG power spectra and functional connectivity among channels. We then used this information to build an automatic valence classifier. The experimental results showed that the functional connectivity at the highest frequency bands (i.e., > 30 Hz) was most sensitive to arousal modulation. Specifically, high connectivity over the right hemisphere occurred during pleasant elicitation, whereas that over the left hemisphere occurred during negative elicitation. In addition, short-range connections in the frontal regions became weaker with increased arousal level, whereas long-range connections were enhanced. Concerning the spectral analysis, the most significant valence-dependent changes were found at intermediate arousing elicitations over the prefrontal and occipital regions. The automatic valence classification showed a recognition accuracy of up to 86.37 percent.

Objective: The quantification of functional brain–heart interplay through the dynamics of the central and autonomic nervous systems may provide effective biomarkers for cognitive, emotional, and autonomic state changes. Despite several computational models were proposed to this end, none provides a directional estimation of such interplay in a time-resolved and probabilistic fashion. Methods: In this study, a multivariate inhomogeneous point-process model for heartbeat dynamics is employed to derive subject-specific, time-resolved, functional estimates of the directional interplay occurring from the brain to the heart, whose activity is represented by electroencephalography and R-peaks intervals series. An inverse-Gaussian probability density function is used to predict heartbeat events as a function of neural dynamics, which is modeled as an exogenous input to the autoregressive cardiac dynamics. Results: The performance is evaluated using heart rate variability and electroencephalography series gathered from 24 healthy volunteers undergoing a cold-pressor test, and the modeling goodness-of-fit is assessed through the time-rescaling theorem. The results suggest that cortical dynamics drives heartbeat series with specific time delays in the range of 30s to 60s and 90s to 120s from the peripheral thermal stress onset. Conclusion: The proposed framework provides novel insights in human neurophysiology, exploiting a fully probabilistic definition of the continuous functional brain–heart interplay.

In this work, we resolve a big challenge that most current image quality metrics (IQMs) are unavailable across different image contents, especially simultaneously coping with natural scene (NS) images or screen content (SC) images. By comparison with existing works, this paper deploys on-line and off-line data for proposing a unified no-reference (NR) IQM, not only applied to different distortion types and intensities but also to various image contents including classical NS images and prevailing SC images. Our proposed NR IQM is developed with two data-driven learning processes following feature extraction, which is based on scene statistic models, free-energy brain principle, and human visual system (HVS) characteristics. In the first process, the scene statistic models and an image retrieve technique are combined, based on on-line and off-line training instances, to derive a novel loose classifier for retrieving clean images and helping to infer the image content. In the second process, the features extracted by incorporating the inferred image content, free-energy and low-level perceptual characteristics of the HVS are learned by utilizing off-line training samples to analyze the distortion types and intensities and thereby to predict the image quality. The two processes mentioned above depend on a gigantic quantity of training data, much exceeding the number of images applied to performance validation, and thus make our model's performance more reliable. Through extensive experiments, it has been validated that the proposed blind IQM is capable of simultaneously inferring the quality of NS and SC images, and it has attained superior performance as compared with popular and state-of-the-art IQMs on the subjective NS and SC image quality databases. The source code of our model will be released with the publication of the paper at https://kegu.netlify.com .

Electromagnetic brain imaging is the reconstruction of brain activity from non-invasive recordings of the magnetic fields and electric potentials. An enduring challenge in this imaging modality is estimating the number, location, and time course of sources, especially for the reconstruction of distributed brain sources with complex spatial extent. Here, we introduce a novel robust empirical Bayesian algorithm that enables better reconstruction of distributed brain source activity with two key ideas: kernel smoothing and hyperparameter tiling. Since the proposed algorithm builds upon many of the performance features of the sparse source reconstruction algorithm - Champagne and we refer to this algorithm as Smooth Champagne. Smooth Champagne is robust to the effects of high levels of noise, interference, and highly correlated brain source activity. Simulations demonstrate excellent performance of Smooth Champagne when compared to benchmark algorithms in accurately determining the spatial extent of distributed source activity. Smooth Champagne also accurately reconstructs real MEG and EEG data.

For robot intelligence and human-robot interaction (HRI), complex decision-making, interpretation, and adaptive planning processes are great challenges. These require recursive task processing and meta-cognitive reasoning mechanism. Naturally, the human brain realizes these cognitive skills by prefrontal cortex which is a part of the neocortex. Previous studies about neurocognitive robotics would not meet these requirements. Thus, it is aimed at developing a brain-inspired robot control architecture that performs spatial-temporal and emotional reasoning. In this study, we present a novel solution that covers a computational model of the prefrontal cortex for humanoid robots. Computational mechanisms are mainly placed on the bio-physical plausible neural structures embodied in different dynamics. The main components of the system are composed of several computational modules including dorsolateral, ventrolateral, anterior, and medial prefrontal regions. Also, it is responsible for organizing the working memory. A reinforcement meta-learning based explainable artificial intelligence (xAI) procedure is applied to the working memory regions of the computational prefrontal cortex model. Experimental evaluation and verification tests are processed by the developed software framework embodied in the humanoid robot platform. The humanoid robots' perceptual states and cognitive processes including emotion, attention, and intention-based reasoning skills can be observed and controlled via the developed software. Several interaction scenarios are implemented to monitor and evaluate the model's performance.

Tucker decomposition can provide an intuitive summary to understand brain function by decomposing multi-subject fMRI data into a core tensor and multiple factor matrices, and was mostly used to extract functional connectivity patterns across time/subjects using orthogonality constraints. However, these algorithms are unsuitable for extracting common spatial and temporal patterns across subjects due to distinct characteristics such as high-level noise. Motivated by a successful application of Tucker decomposition to image denoising and the intrinsic sparsity of spatial activations in fMRI, we propose a low-rank Tucker-2 model with spatial sparsity constraint to analyze multi-subject fMRI data. More precisely, we propose to impose a sparsity constraint on spatial maps by using an lp norm (0

Epilepsy is a neurological disorder arising from anomalies of the electrical activity in the brain, affecting about 65 millions individuals worldwide. Objective: This paper proposes a patient-specific approach for short-term prediction (i.e., within few minutes) of epileptic seizures. Methods: We use noninvasive EEG data, since the aim is exploring the possibility of developing a noninvasive monitoring/control device for the prediction of seizures. Our approach is based on finding synchronization patterns in the EEG that allow to distinguish in real time preictal from interictal states. In practice, we develop easily computable functions over a graph model to capture the variations in the synchronization, and employ a classifier for identifying the preictal state. Results: We compare two state-of-the-art classification algorithms and a simple and computationally inexpensive threshold-based classifier developed ad hoc. Results on publicly available scalp EEG database and on scalp data of the patients of the Unit of Neurology and Neurophysiology at University of Siena show that this simple and computationally viable processing is able to highlight the changes in synchronization when a seizure is approaching. Conclusion and significance: The proposed approach, characterized by low computational requirements and by the use of noninvasive techniques, is a step toward the development of portable and wearable devices for real-life use.

Although the recent years have witnessed a growing interest in functional connectivity (FC) through brain sources, the FC in extreme situations has not been completely elucidated. This paper is aimed at investigating whether the expertise acquired during the deep-sea diving is reflected in FC in a group of professional divers (PDs) compared to a group of new divers (NDs), and how it could affect the concentration and stress levels. The sources of brain frequency rhythms, derived by the electroencephalography acquisition in a hyperbaric chamber, were extracted in different frequency bands and the corresponding FC was estimated in order to compare the two groups. The results highlighted a significant decrease of the alpha source in PDs during air breathing and a significant increase of the upper beta source over central areas at the beginning of post-oxygen air, as well as an increase of beta FC between fronto-temporal regions in the last minutes of oxygen breathing and in the early minutes of post-oxygen air. This provides evidence in support of the hypothesis that experience and expertise differences would modulate brain networks. These experiments provided the unique opportunity of investigating the impact of the neurophysiological activity in simulated critical scenarios in view of the investigation in real sea-water experiments.

A high number of studies have already demonstrated an electroencephalography (EEG)-based emotion recognition system with moderate results. Emotions are classified into discrete and dimensional models. We focused on the latter that incorporates valence and arousal dimensions. The mainstream methodology is the extraction of univariate measures derived from EEG activity from various frequencies classifying trials into low/high valence and arousal levels. Here, we evaluated brain connectivity within and between brain frequencies under the multiplexity framework. We analyzed an EEG database called DEAP that contains EEG responses to video stimuli and users' emotional self-assessments. We adopted a dynamic functional connectivity analysis under the notion of our dominant coupling model (DoCM). DoCM detects the dominant coupling mode per pair of EEG sensors, which can be either within frequencies coupling (intra) or between frequencies coupling (cross-frequency). DoCM revealed an integrated dynamic functional connectivity graph (IDFCG) that keeps both the strength and the preferred dominant coupling mode. We aimed to create a connectomic mapping of valence-arousal map via employing features derive from IDFCG. Our results outperformed previous findings succeeding to predict in a high accuracy participants' ratings in valence and arousal dimensions based on a flexibility index of dominant coupling modes.

Objective: Bi-Frequency Symmetry Difference (BFSD)-EIT can detect, localize and identify unilateral perturbations in symmetric scenes. Here, we test the viability and robustness of BFSD-EIT in stroke diagnosis. Methods: A realistic 4-layer Finite Element Method (FEM) head model with and without bleed and clot lesions is developed. Performance is assessed with test parameters including: measurement noise, electrode placement errors, contact impedance errors, deviations in assumed tissue conductivity, deviations in assumed anatomy, and a frequency-dependent background. A final test is performed using ischemic patient data. Results are assessed using images and quantitative metrics. Results: BFSD-EIT may be feasible for stroke diagnosis if a signal-to-noise ratio (SNR) of ≥60dB is achievable. Sensitivity to errors in electrode positioning is seen with a tolerance of only ±5mm, but a tolerance of up to ±30mm is possible if symmetry is maintained between symmetrically opposite partner electrodes. The technique is robust to errors in contact impedance and assumed tissue conductivity up to at least ±50%. Asymmetric internal anatomy affects performance but may be tolerable for tissues with frequency-dependent conductivity. Errors in assumed external geometry marginally affect performance. A frequency-dependent background does not affect performance with carefully chosen frequency points or use of multiple frequency points across a band. The Global Left-Hand Side (LHS) & Right-Hand Side (RHS) Mean Intensity metric is particularly robust to errors. Conclusion: BFSD-EIT is a promising technique for stroke diagnosis, provided parameters are within the tolerated ranges. Significance: BFSD-EIT may prove an important step forward in imaging of static scenes such as stroke. The research leading to these results has received funding from the European Research Council under the European Union’s Horizon 2020 Programme/ ERC Grant Agreement BioElecPro n.637780, Science Foundation Ireland (SFI) grant number 15/ERCS/3276, the Hardiman Research Scholarship from NUIG, the charity RESPECT and the People Programme (Marie Curie Actions) of the European Union’s Seventh Framework Programme (FP7/2007-2013) under REA Grant Agreement no. PCOFUND-GA-2013-608728. J Avery was supported by the NIHR Imperial BRC. *B. McDermott, M. O’Halloran and E. Porter are with the Translational Medical Device Lab, National University of Ireland Galway. J Avery is with The Department of Surgery & Cancer, Imperial College London, London, UK (correspondence e-mail: b.mcdermott3@nuigalway.ie). peer-reviewed

copyright 2018 IEEE, Human brain connectivity is complex. Graph-theory-based analysis has become a powerful and popular approach for analyzing brain imaging data, largely because of its potential to quantitatively illuminate the networks, the static architecture in structure and function, the organization of dynamic behavior over time, and disease related brain changes. The first step in creating brain graphs is to define the nodes and edges connecting them. We review a number of approaches for defining brain nodes including fixed versus data-driven nodes. Expanding the narrow view of most studies which focus on static and/or single modality brain connectivity, we also survey advanced approaches and their performances in building dynamic and multimodal brain graphs. We show results from both simulated and real data from healthy controls and patients with mental illnesses. We outline the advantages and challenges of these various techniques. By summarizing and inspecting recent studies which analyzed brain imaging data based on graph theory, this paper provides a guide for developing new powerful tools to explore complex brain networks.

Visual tracking has long been studied in computer vision, and it has many practical applications such as surveillance and security, traffic control, human-computer interaction, and activity or behavior recognition to mention but a few. Head tracking attempts to follow a person's head within a video sequence. This paper presents a methodology that automatically designs an artificial dorsal stream for the problem of head tracking. Multiple visual operators are synthesized to obtain several visual and conspicuity maps that are fused into a saliency map, which is converted to a binary image, thus defining the proto-object. The automatic design of visual attention programs for the problem of head tracking is achieved through an optimization process following the Darwinian paradigm of artificial evolution. Artificial brains are synthesized using multiple visual operators embedded within a complex hierarchical procedure consisting of several key processes such as center-surround mechanisms, normalization, and pyramid-scale processes. The proposed strategy robustly handles many difficulties including occlusion, distraction, and illumination, and the resulting programs are real-time systems that are able to track a person's head with enough accuracy to automatically control the camera. Extensive experimentation shows that the proposed method outperforms several state-of-the-art methods in the challenging problem of head tracking.

International audience; This article deals with microwave tomography for brain stroke imaging using state-of-the-art numerical modeling and massively parallel computing. Iterative microwave tomographic imaging requires the solution of an inverse problem based on a minimization algorithm (e.g., gradient based) with successive solutions of a direct problem such as the accurate modeling of a whole-microwave measurement system. Moreover, a sufficiently high number of unknowns is required to accurately represent the solution. As the system will be used for detecting a brain stroke (ischemic or hemorrhagic) as well as for monitoring during the treatment, the running times for the reconstructions should be reasonable. The method used is based on high-order finite elements, parallel preconditioners from the domain decomposition method and domain-specific language with the opensource FreeFEM++ solver.

This study presents a voxel-based multiple regression analysis of different magnetic resonance image modalities, including anatomical T1-weighted, T2(*) relaxometry, and diffusion tensor imaging. Quantitative parameters sensitive to complementary brain tissue alterations, including morphometric atrophy, mineralization, microstructural damage, and anisotropy loss, were compared in a linear physiological aging model in 140 healthy subjects (range 20-74 years). The performance of different predictors and the identification of the best biomarker of age-induced structural variation were compared without a priori anatomical knowledge. The best quantitative predictors in several brain regions were iron deposition and microstructural damage, rather than macroscopic tissue atrophy. Age variations were best resolved with a combination of markers, suggesting that multiple predictors better capture age-induced tissue alterations. The results of the linear model were used to predict apparent age in different regions of individual brain. This approach pointed to a number of novel applications that could potentially help highlighting areas particularly vulnerable to disease.

Mimicking the human brain to achieve human-level cognition performance has been a core challenge in artificial intelligence research for decades. Humans are very efficient in capturing the most important information while being exposed to a plethora of different stimuli, a capability that is used to represent and understand their surroundings in a concise fashion. Machine learning research has made considerable progress toward cloning such a human capability with innovative techniques like deep learning, feature learning, incremental learning, and so on. In this article, an overview of the mainstream brain-inspired architectures and research directions proposed over the past decade is provided. In addition, a novel architecture exploiting the strengths of the current methods is proposed. Preliminary results demonstrate that it is able to achieve state-of-the-art results in a more efficient way.