Toward a computational theory of manifold untangling: from global embedding to local flattening
It has been hypothesized that the ventral stream processing for object recognition is based on a mechanism called cortically local subspace untangling. A mathematical abstraction of object recognition by the visual cortex is how to untangle the manifolds associated with different object categories. Such a manifold untangling problem is closely related to the celebrated kernel trick in metric space. In this paper, we conjecture that there is a more general solution to manifold untangling in the...
Read more...
It has been hypothesized that the ventral stream processing for object recognition is based on a mechanism called cortically local subspace untangling. A mathematical abstraction of object recognition by the visual cortex is how to untangle the manifolds associated with different object categories. Such a manifold untangling problem is closely related to the celebrated kernel trick in metric space. In this paper, we conjecture that there is a more general solution to manifold untangling in the...
Read more...
Information-theoretic analysis of Hierarchical Temporal Memory-Spatial Pooler algorithm with a new upper bound for the standard information bottleneck method
Hierarchical Temporal Memory (HTM) is an unsupervised algorithm in machine learning. It models several fundamental neocortical computational principles. Spatial Pooler (SP) is one of the main components of the HTM, which continuously encodes streams of binary input from various layers and regions into sparse distributed representations. In this paper, the goal is to evaluate the sparsification in the SP algorithm from the perspective of information theory by the information bottleneck (IB),...
Read more...
Hierarchical Temporal Memory (HTM) is an unsupervised algorithm in machine learning. It models several fundamental neocortical computational principles. Spatial Pooler (SP) is one of the main components of the HTM, which continuously encodes streams of binary input from various layers and regions into sparse distributed representations. In this paper, the goal is to evaluate the sparsification in the SP algorithm from the perspective of information theory by the information bottleneck (IB),...
Read more...
Reservoir based spiking models for univariate Time Series Classification
A variety of advanced machine learning and deep learning algorithms achieve state-of-the-art performance on various temporal processing tasks. However, these methods are heavily energy inefficient-they run mainly on the power hungry CPUs and GPUs. Computing with Spiking Networks, on the other hand, has shown to be energy efficient on specialized neuromorphic hardware, e.g., Loihi, TrueNorth, SpiNNaker, etc. In this work, we present two architectures of spiking models, inspired from the theory of...
Read more...
A variety of advanced machine learning and deep learning algorithms achieve state-of-the-art performance on various temporal processing tasks. However, these methods are heavily energy inefficient-they run mainly on the power hungry CPUs and GPUs. Computing with Spiking Networks, on the other hand, has shown to be energy efficient on specialized neuromorphic hardware, e.g., Loihi, TrueNorth, SpiNNaker, etc. In this work, we present two architectures of spiking models, inspired from the theory of...
Read more...
Optogenetic manipulation of inhibitory interneurons can be used to validate a model of spatiotemporal sequence learning
The brain uses temporal information to link discrete events into memory structures supporting recognition, prediction, and a wide variety of complex behaviors. It is still an open question how experience-dependent synaptic plasticity creates memories including temporal and ordinal information. Various models have been proposed to explain how this could work, but these are often difficult to validate in a living brain. A recent model developed to explain sequence learning in the visual cortex...
Read more...
The brain uses temporal information to link discrete events into memory structures supporting recognition, prediction, and a wide variety of complex behaviors. It is still an open question how experience-dependent synaptic plasticity creates memories including temporal and ordinal information. Various models have been proposed to explain how this could work, but these are often difficult to validate in a living brain. A recent model developed to explain sequence learning in the visual cortex...
Read more...
Corrigendum: An initial prediction and fine-tuning model based on improving GCN for 3D human motion prediction
This corrects the article DOI: 10.3389/fncom.2023.1145209..
Read more...
This corrects the article DOI: 10.3389/fncom.2023.1145209..
Read more...
Covariance properties under natural image transformations for the generalised Gaussian derivative model for visual receptive fields
The property of covariance, also referred to as equivariance, means that an image operator is well-behaved under image transformations, in the sense that the result of applying the image operator to a transformed input image gives essentially a similar result as applying the same image transformation to the output of applying the image operator to the original image. This paper presents a theory of geometric covariance properties in vision, developed for a generalised Gaussian derivative model...
Read more...
The property of covariance, also referred to as equivariance, means that an image operator is well-behaved under image transformations, in the sense that the result of applying the image operator to a transformed input image gives essentially a similar result as applying the same image transformation to the output of applying the image operator to the original image. This paper presents a theory of geometric covariance properties in vision, developed for a generalised Gaussian derivative model...
Read more...
Robust and efficient representations of dynamic stimuli in hierarchical neural networks via temporal smoothing
INTRODUCTION: Efficient coding that minimizes informational redundancy of neural representations is a widely accepted neural coding principle. Despite the benefit, maximizing efficiency in neural coding can make neural representation vulnerable to random noise. One way to achieve robustness against random noise is smoothening neural responses. However, it is not clear whether the smoothness of neural responses can hold robust neural representations when dynamic stimuli are processed through a...
Read more...
INTRODUCTION: Efficient coding that minimizes informational redundancy of neural representations is a widely accepted neural coding principle. Despite the benefit, maximizing efficiency in neural coding can make neural representation vulnerable to random noise. One way to achieve robustness against random noise is smoothening neural responses. However, it is not clear whether the smoothness of neural responses can hold robust neural representations when dynamic stimuli are processed through a...
Read more...
Corrigendum: Accurate few-shot object counting with Hough matching feature enhancement
This corrects the article DOI: 10.3389/fncom.2023.1145219..
Read more...
This corrects the article DOI: 10.3389/fncom.2023.1145219..
Read more...
Editorial: Decoding novel therapeutic targets, biomarkers, and drug development strategies against neurodegenerative disorders-A multi-omics approach
No abstract
Read more...
No abstract
Read more...
Distinctive properties of biological neural networks and recent advances in bottom-up approaches toward a better biologically plausible neural network
Although it may appear infeasible and impractical, building artificial intelligence (AI) using a bottom-up approach based on the understanding of neuroscience is straightforward. The lack of a generalized governing principle for biological neural networks (BNNs) forces us to address this problem by converting piecemeal information on the diverse features of neurons, synapses, and neural circuits into AI. In this review, we described recent attempts to build a biologically plausible neural...
Read more...
Although it may appear infeasible and impractical, building artificial intelligence (AI) using a bottom-up approach based on the understanding of neuroscience is straightforward. The lack of a generalized governing principle for biological neural networks (BNNs) forces us to address this problem by converting piecemeal information on the diverse features of neurons, synapses, and neural circuits into AI. In this review, we described recent attempts to build a biologically plausible neural...
Read more...
Controlling neocortical epileptic seizures using forced temporal spike-time stimulation: an <em>in silico</em> computational study
Epileptic seizure is typically characterized by highly synchronized episodes of neural activity. Existing stimulation therapies focus purely on suppressing the pathologically synchronized neuronal firing patterns during the ictal (seizure) period. While these strategies are effective in suppressing seizures when they occur, they fail to prevent the re-emergence of seizures once the stimulation is turned off. Previously, we developed a novel neurostimulation motif, which we refer to as "Forced...
Read more...
Epileptic seizure is typically characterized by highly synchronized episodes of neural activity. Existing stimulation therapies focus purely on suppressing the pathologically synchronized neuronal firing patterns during the ictal (seizure) period. While these strategies are effective in suppressing seizures when they occur, they fail to prevent the re-emergence of seizures once the stimulation is turned off. Previously, we developed a novel neurostimulation motif, which we refer to as "Forced...
Read more...
Examining electroencephalogram signatures of people with multiple sclerosis using a nonlinear dynamics approach: a systematic review and bibliographic analysis
CONCLUSION: Although nonlinear EEG analysis of MS is a relatively novel area of research, the findings have been demonstrated to be informative and effective. The most frequently used nonlinear dynamics analyses were fractal dimension, recurrence quantification analysis, mutual information, and coherence. Each analysis selected provided a unique assessment to fulfill the objective of this review. While considering the limitations discussed, there is a promising path forward using nonlinear...
Read more...
CONCLUSION: Although nonlinear EEG analysis of MS is a relatively novel area of research, the findings have been demonstrated to be informative and effective. The most frequently used nonlinear dynamics analyses were fractal dimension, recurrence quantification analysis, mutual information, and coherence. Each analysis selected provided a unique assessment to fulfill the objective of this review. While considering the limitations discussed, there is a promising path forward using nonlinear...
Read more...
Editorial: The new frontier in brain network physiology: from temporal dynamics to the principles of integration in physiological brain networks
No abstract
Read more...
No abstract
Read more...
Online spike-based recognition of digits with ultrafast microlaser neurons
Classification and recognition tasks performed on photonic hardware-based neural networks often require at least one offline computational step, such as in the increasingly popular reservoir computing paradigm. Removing this offline step can significantly improve the response time and energy efficiency of such systems. We present numerical simulations of different algorithms that utilize ultrafast photonic spiking neurons as receptive fields to allow for image recognition without an offline...
Read more...
Classification and recognition tasks performed on photonic hardware-based neural networks often require at least one offline computational step, such as in the increasingly popular reservoir computing paradigm. Removing this offline step can significantly improve the response time and energy efficiency of such systems. We present numerical simulations of different algorithms that utilize ultrafast photonic spiking neurons as receptive fields to allow for image recognition without an offline...
Read more...
Empirical mode decomposition of local field potential data from optogenetic experiments
INTRODUCTION: This study investigated the effects of cocaine administration and parvalbumin-type interneuron stimulation on local field potentials (LFPs) recorded in vivo from the medial prefrontal cortex (mPFC) of six mice using optogenetic tools.
Read more...
INTRODUCTION: This study investigated the effects of cocaine administration and parvalbumin-type interneuron stimulation on local field potentials (LFPs) recorded in vivo from the medial prefrontal cortex (mPFC) of six mice using optogenetic tools.
Read more...
Convolutional neural networks for vision neuroscience: significance, developments, and outstanding issues
Convolutional Neural Networks (CNN) are a class of machine learning models predominately used in computer vision tasks and can achieve human-like performance through learning from experience. Their striking similarities to the structural and functional principles of the primate visual system allow for comparisons between these artificial networks and their biological counterparts, enabling exploration of how visual functions and neural representations may emerge in the real brain from a limited...
Read more...
Convolutional Neural Networks (CNN) are a class of machine learning models predominately used in computer vision tasks and can achieve human-like performance through learning from experience. Their striking similarities to the structural and functional principles of the primate visual system allow for comparisons between these artificial networks and their biological counterparts, enabling exploration of how visual functions and neural representations may emerge in the real brain from a limited...
Read more...
Functional extreme learning machine
INTRODUCTION: Extreme learning machine (ELM) is a training algorithm for single hidden layer feedforward neural network (SLFN), which converges much faster than traditional methods and yields promising performance. However, the ELM also has some shortcomings, such as structure selection, overfitting and low generalization performance.
Read more...
INTRODUCTION: Extreme learning machine (ELM) is a training algorithm for single hidden layer feedforward neural network (SLFN), which converges much faster than traditional methods and yields promising performance. However, the ELM also has some shortcomings, such as structure selection, overfitting and low generalization performance.
Read more...
Editorial: Affective brain-computer interface in emotion artificial intelligence and medical engineering
No abstract
Read more...
No abstract
Read more...
Feature separation and adversarial training for the patient-independent detection of epileptic seizures
An epileptic seizure is the external manifestation of abnormal neuronal discharges, which seriously affecting physical health. The pathogenesis of epilepsy is complex, and the types of epileptic seizures are diverse, resulting in significant variation in epileptic seizure data between subjects. If we feed epilepsy data from multiple patients directly into the model for training, it will lead to underfitting of the model. To overcome this problem, we propose a robust epileptic seizure detection...
Read more...
An epileptic seizure is the external manifestation of abnormal neuronal discharges, which seriously affecting physical health. The pathogenesis of epilepsy is complex, and the types of epileptic seizures are diverse, resulting in significant variation in epileptic seizure data between subjects. If we feed epilepsy data from multiple patients directly into the model for training, it will lead to underfitting of the model. To overcome this problem, we propose a robust epileptic seizure detection...
Read more...
Interpreting the decisions of CNNs via influence functions
An understanding of deep neural network decisions is based on the interpretability of model, which provides explanations that are understandable to human beings and helps avoid biases in model predictions. This study investigates and interprets the model output based on images from the training dataset, i.e., to debug the results of a network model in relation to the training dataset. Our objective was to understand the behavior (specifically, class prediction) of deep learning models through...
Read more...
An understanding of deep neural network decisions is based on the interpretability of model, which provides explanations that are understandable to human beings and helps avoid biases in model predictions. This study investigates and interprets the model output based on images from the training dataset, i.e., to debug the results of a network model in relation to the training dataset. Our objective was to understand the behavior (specifically, class prediction) of deep learning models through...
Read more...