scholarly journals Brain-inspired automated visual object discovery and detection

2018 ◽  
Vol 116 (1) ◽  
pp. 96-105 ◽  
Author(s):  
Lichao Chen ◽  
Sudhir Singh ◽  
Thomas Kailath ◽  
Vwani Roychowdhury
Keyword(s):  
Unsupervised Learning ◽  
Markov Random Fields ◽  
Large Scale ◽  
Learning Algorithm ◽  
Visual Object ◽  
Contextual Data ◽  
Recent Computer ◽  
Object Models ◽  
Detection And Localization ◽  
The Brain

Despite significant recent progress, machine vision systems lag considerably behind their biological counterparts in performance, scalability, and robustness. A distinctive hallmark of the brain is its ability to automatically discover and model objects, at multiscale resolutions, from repeated exposures to unlabeled contextual data and then to be able to robustly detect the learned objects under various nonideal circumstances, such as partial occlusion and different view angles. Replication of such capabilities in a machine would require three key ingredients: (i) access to large-scale perceptual data of the kind that humans experience, (ii) flexible representations of objects, and (iii) an efficient unsupervised learning algorithm. The Internet fortunately provides unprecedented access to vast amounts of visual data. This paper leverages the availability of such data to develop a scalable framework for unsupervised learning of object prototypes—brain-inspired flexible, scale, and shift invariant representations of deformable objects (e.g., humans, motorcycles, cars, airplanes) comprised of parts, their different configurations and views, and their spatial relationships. Computationally, the object prototypes are represented as geometric associative networks using probabilistic constructs such as Markov random fields. We apply our framework to various datasets and show that our approach is computationally scalable and can construct accurate and operational part-aware object models much more efficiently than in much of the recent computer vision literature. We also present efficient algorithms for detection and localization in new scenes of objects and their partial views.

scholarly journals Efficient Similarity-Preserving Unsupervised Learning using Modular Sparse Distributed Codes and Novelty-Contingent Noise

2020 ◽  
Author(s):  
Rod Rinkus
Keyword(s):  
Unsupervised Learning ◽  
Learning Algorithm ◽  
Fixed Time ◽  
Cell Assembly ◽  
Single Trial ◽  
Essential Questions ◽  
Similarity Preserving ◽  
The Brain ◽  
Modular Nature ◽  
Distributed Codes

AbstractThere is increasing realization in neuroscience that information is represented in the brain, e.g., neocortex, hippocampus, in the form sparse distributed codes (SDCs), a kind of cell assembly. Two essential questions are: a) how are such codes formed on the basis of single trials, and how is similarity preserved during learning, i.e., how do more similar inputs get mapped to more similar SDCs. I describe a novel Modular Sparse Distributed Code (MSDC) that provides simple, neurally plausible answers to both questions. An MSDC coding field (CF) consists of Q WTA competitive modules (CMs), each comprised of K binary units (analogs of principal cells). The modular nature of the CF makes possible a single-trial, unsupervised learning algorithm that approximately preserves similarity and crucially, runs in fixed time, i.e., the number of steps needed to store an item remains constant as the number of stored items grows. Further, once items are stored as MSDCs in superposition and such that their intersection structure reflects input similarity, both fixed time best-match retrieval and fixed time belief update (updating the probabilities of all stored items) also become possible. The algorithm’s core principle is simply to add noise into the process of choosing a code, i.e., choosing a winner in each CM, which is proportional to the novelty of the input. This causes the expected intersection of the code for an input, X, with the code of each previously stored input, Y, to be proportional to the similarity of X and Y. Results demonstrating these capabilities for spatial patterns are given in the appendix.

scholarly journals Human EEG recordings for 1,854 concepts presented in rapid serial visual presentation streams

2022 ◽  
Vol 9 (1) ◽  
Author(s):  
Tijl Grootswagers ◽  
Ivy Zhou ◽  
Amanda K. Robinson ◽  
Martin N. Hebart ◽  
Thomas A. Carlson
Keyword(s):  
Large Scale ◽  
Visual Presentation ◽  
Semantic Knowledge ◽  
Human Vision ◽  
Visual Object ◽  
Neural Basis ◽  
Object Knowledge ◽  
Object Processing ◽  
Eeg Recordings ◽  
The Brain

AbstractThe neural basis of object recognition and semantic knowledge has been extensively studied but the high dimensionality of object space makes it challenging to develop overarching theories on how the brain organises object knowledge. To help understand how the brain allows us to recognise, categorise, and represent objects and object categories, there is a growing interest in using large-scale image databases for neuroimaging experiments. In the current paper, we present THINGS-EEG, a dataset containing human electroencephalography responses from 50 subjects to 1,854 object concepts and 22,248 images in the THINGS stimulus set, a manually curated and high-quality image database that was specifically designed for studying human vision. The THINGS-EEG dataset provides neuroimaging recordings to a systematic collection of objects and concepts and can therefore support a wide array of research to understand visual object processing in the human brain.

scholarly journals Unsupervised Learning Method for SAR Image Classification Based on Spiking Neural Network

2021 ◽  
Author(s):  
Jiankun Chen ◽  
Xiaolan Qiu ◽  
Chuanzhao Han ◽  
Yirong Wu
Keyword(s):  
Neural Network ◽  
Unsupervised Learning ◽  
Image Classification ◽  
Spatial Information ◽  
Learning Algorithm ◽  
Image Interpretation ◽  
Spike Timing ◽  
Spiking Neural Network ◽  
Sar Image ◽  
The Brain

Recent neuroscience research results show that the nerve information in the brain is not only encoded by the spatial information. Spiking neural network based on pulse frequency coding plays a very important role in dealing with the problem of brain signal, especially complicated space-time information. In this paper, an unsupervised learning algorithm for bilayer feedforward spiking neural networks based on spike-timing dependent plasticity (STDP) competitiveness is proposed and applied to SAR image classification on MSTAR for the first time. The SNN learns autonomously from the input value without any labeled signal and the overall classification accuracy of SAR targets reached 80.8%. The experimental results show that the algorithm adopts the synaptic neurons and network structure with stronger biological rationality, and has the ability to classify targets on SAR image. Meanwhile, the feature map extraction ability of neurons is visualized by the generative property of SNN, which is a beneficial attempt to apply the brain-like neural network into SAR image interpretation.

Implantable neural interfaces

2018 ◽  
Author(s):  
Stefano Vassanelli
Keyword(s):  
Brain Function ◽  
Large Scale ◽  
Ionic Channels ◽  
Patch Clamp Technique ◽  
Advantages And Disadvantages ◽  
Optogenetic Stimulation ◽  
Physical Interfaces ◽  
The Brain

Establishing direct communication with the brain through physical interfaces is a fundamental strategy to investigate brain function. Starting with the patch-clamp technique in the seventies, neuroscience has moved from detailed characterization of ionic channels to the analysis of single neurons and, more recently, microcircuits in brain neuronal networks. Development of new biohybrid probes with electrodes for recording and stimulating neurons in the living animal is a natural consequence of this trend. The recent introduction of optogenetic stimulation and advanced high-resolution large-scale electrical recording approaches demonstrates this need. Brain implants for real-time neurophysiology are also opening new avenues for neuroprosthetics to restore brain function after injury or in neurological disorders. This chapter provides an overview on existing and emergent neurophysiology technologies with particular focus on those intended to interface neuronal microcircuits in vivo. Chemical, electrical, and optogenetic-based interfaces are presented, with an analysis of advantages and disadvantages of the different technical approaches.

What Has Direct Cortical and Subcortical Electrostimulation Taught Us about Neurolinguistics?

2019 ◽  
pp. 185-211
Author(s):  
Hugues Duffau
Keyword(s):  
White Matter ◽  
Large Scale ◽  
Functional Neuroimaging ◽  
Great Accuracy ◽  
Subcortical White Matter ◽  
Cerebral Lesions ◽  
Physiological Basis ◽  
Postoperative Mri ◽  
The Brain

Investigating the neural and physiological basis of language is one of the most important challenges in neurosciences. Direct electrical stimulation (DES), usually performed in awake patients during surgery for cerebral lesions, is a reliable tool for detecting both cortical and subcortical (white matter and deep grey nuclei) regions crucial for cognitive functions, especially language. DES transiently interacts locally with a small cortical or axonal site, but also nonlocally, as the focal perturbation will disrupt the entire subnetwork sustaining a given function. Thus, in contrast to functional neuroimaging, DES represents a unique opportunity to identify with great accuracy and reproducibility, in vivo in humans, the structures that are actually indispensable to the function, by inducing a transient virtual lesion based on the inhibition of a subcircuit lasting a few seconds. Currently, this is the sole technique that is able to directly investigate the functional role of white matter tracts in humans. Thus, combining transient disturbances elicited by DES with the anatomical data provided by pre- and postoperative MRI enables to achieve reliable anatomo-functional correlations, supporting a network organization of the brain, and leading to the reappraisal of models of language representation. Finally, combining serial peri-operative functional neuroimaging and online intraoperative DES allows the study of mechanisms underlying neuroplasticity. This chapter critically reviews the basic principles of DES, its advantages and limitations, and what DES can reveal about the neural foundations of language, that is, the large-scale distribution of language areas in the brain, their connectivity, and their ability to reorganize.

scholarly journals Content-Based Estimation of Brain MRI Tilt in Three Orthogonal Directions

2021 ◽  
Author(s):  
Pooja Prabhu ◽  
A. K. Karunakar ◽  
Sanjib Sinha ◽  
N. Mariyappa ◽  
G. K. Bhargava ◽  
...  
Keyword(s):  
Large Scale ◽  
Brain Mri ◽  
Similarity Measures ◽  
Principal Component ◽  
Brain Anatomy ◽  
Morphological Operations ◽  
Mr Images ◽  
Tilt Correction ◽  
Brain Mr Images ◽  
The Brain

AbstractIn a general scenario, the brain images acquired from magnetic resonance imaging (MRI) may experience tilt, distorting brain MR images. The tilt experienced by the brain MR images may result in misalignment during image registration for medical applications. Manually correcting (or estimating) the tilt on a large scale is time-consuming, expensive, and needs brain anatomy expertise. Thus, there is a need for an automatic way of performing tilt correction in three orthogonal directions (X, Y, Z). The proposed work aims to correct the tilt automatically by measuring the pitch angle, yaw angle, and roll angle in X-axis, Z-axis, and Y-axis, respectively. For correction of the tilt around the Z-axis (pointing to the superior direction), image processing techniques, principal component analysis, and similarity measures are used. Also, for correction of the tilt around the X-axis (pointing to the right direction), morphological operations, and tilt correction around the Y-axis (pointing to the anterior direction), orthogonal regression is used. The proposed approach was applied to adjust the tilt observed in the T1- and T2-weighted MR images. The simulation study with the proposed algorithm yielded an error of 0.40 ± 0.09°, and it outperformed the other existing studies. The tilt angle (in degrees) obtained is ranged from 6.2 ± 3.94, 2.35 ± 2.61, and 5 ± 4.36 in X-, Z-, and Y-directions, respectively, by using the proposed algorithm. The proposed work corrects the tilt more accurately and robustly when compared with existing studies.

A new method to predict anomaly in brain network based on graph deep learning

2020 ◽  
Vol 31 (6) ◽  
pp. 681-689
Author(s):  
Jalal Mirakhorli ◽  
Hamidreza Amindavar ◽  
Mojgan Mirakhorli
Keyword(s):  
Deep Learning ◽  
Large Scale ◽  
Brain Plasticity ◽  
Brain Network ◽  
High Order ◽  
Brain Diseases ◽  
Simultaneous Occurrence ◽  
Generative Adversarial Network ◽  
The Brain ◽  
Brain Connections

AbstractFunctional magnetic resonance imaging a neuroimaging technique which is used in brain disorders and dysfunction studies, has been improved in recent years by mapping the topology of the brain connections, named connectopic mapping. Based on the fact that healthy and unhealthy brain regions and functions differ slightly, studying the complex topology of the functional and structural networks in the human brain is too complicated considering the growth of evaluation measures. One of the applications of irregular graph deep learning is to analyze the human cognitive functions related to the gene expression and related distributed spatial patterns. Since a variety of brain solutions can be dynamically held in the neuronal networks of the brain with different activity patterns and functional connectivity, both node-centric and graph-centric tasks are involved in this application. In this study, we used an individual generative model and high order graph analysis for the region of interest recognition areas of the brain with abnormal connection during performing certain tasks and resting-state or decompose irregular observations. Accordingly, a high order framework of Variational Graph Autoencoder with a Gaussian distributer was proposed in the paper to analyze the functional data in brain imaging studies in which Generative Adversarial Network is employed for optimizing the latent space in the process of learning strong non-rigid graphs among large scale data. Furthermore, the possible modes of correlations were distinguished in abnormal brain connections. Our goal was to find the degree of correlation between the affected regions and their simultaneous occurrence over time. We can take advantage of this to diagnose brain diseases or show the ability of the nervous system to modify brain topology at all angles and brain plasticity according to input stimuli. In this study, we particularly focused on Alzheimer’s disease.

scholarly journals Engineered glycomaterial implants orchestrate large-scale functional repair of brain tissue chronically after severe traumatic brain injury

2021 ◽  
Vol 7 (10) ◽  
pp. eabe0207
Author(s):  
Charles-Francois V. Latchoumane ◽  
Martha I. Betancur ◽  
Gregory A. Simchick ◽  
Min Kyoung Sun ◽  
Rameen Forghani ◽  
...  
Keyword(s):  
Traumatic Brain Injury ◽  
Brain Injury ◽  
Severe Traumatic Brain Injury ◽  
Large Scale ◽  
Growth Factor Signaling ◽  
Neuronal Circuit ◽  
Reach To Grasp ◽  
Function Recovery ◽  
Cellular Repair ◽  
The Brain

Severe traumatic brain injury (sTBI) survivors experience permanent functional disabilities due to significant volume loss and the brain’s poor capacity to regenerate. Chondroitin sulfate glycosaminoglycans (CS-GAGs) are key regulators of growth factor signaling and neural stem cell homeostasis in the brain. However, the efficacy of engineered CS (eCS) matrices in mediating structural and functional recovery chronically after sTBI has not been investigated. We report that neurotrophic factor functionalized acellular eCS matrices implanted into the rat M1 region acutely after sTBI significantly enhanced cellular repair and gross motor function recovery when compared to controls 20 weeks after sTBI. Animals subjected to M2 region injuries followed by eCS matrix implantations demonstrated the significant recovery of “reach-to-grasp” function. This was attributed to enhanced volumetric vascularization, activity-regulated cytoskeleton (Arc) protein expression, and perilesional sensorimotor connectivity. These findings indicate that eCS matrices implanted acutely after sTBI can support complex cellular, vascular, and neuronal circuit repair chronically after sTBI.

A Scalable Redefined Stochastic Blockmodel

2021 ◽  
Vol 15 (3) ◽  
pp. 1-28
Author(s):  
Xueyan Liu ◽  
Bo Yang ◽  
Hechang Chen ◽  
Katarzyna Musial ◽  
Hongxu Chen ◽  
...  
Keyword(s):  
Large Scale ◽  
Network Science ◽  
Learning Algorithm ◽  
State Of The Art ◽  
Real World Data ◽  
Computational Overhead ◽  
Stochastic Blockmodel ◽  
Np Hard Problem ◽  
Large Scale Networks ◽  
The Cost

Stochastic blockmodel (SBM) is a widely used statistical network representation model, with good interpretability, expressiveness, generalization, and flexibility, which has become prevalent and important in the field of network science over the last years. However, learning an optimal SBM for a given network is an NP-hard problem. This results in significant limitations when it comes to applications of SBMs in large-scale networks, because of the significant computational overhead of existing SBM models, as well as their learning methods. Reducing the cost of SBM learning and making it scalable for handling large-scale networks, while maintaining the good theoretical properties of SBM, remains an unresolved problem. In this work, we address this challenging task from a novel perspective of model redefinition. We propose a novel redefined SBM with Poisson distribution and its block-wise learning algorithm that can efficiently analyse large-scale networks. Extensive validation conducted on both artificial and real-world data shows that our proposed method significantly outperforms the state-of-the-art methods in terms of a reasonable trade-off between accuracy and scalability. 1

Sign in / Sign up

Export Citation Format

Share Document