Abstract:
:Learning from limited exemplars (few-shot learning) is a fundamental, unsolved problem that has been laboriously explored in the machine learning community. However, current few-shot learners are mostly supervised and rely heavily on a large amount of labeled examples. Unsupervised learning is a more natural procedure for cognitive mammals and has produced promising results in many machine learning tasks. In this paper, we propose an unsupervised feature learning method for few-shot learning. The proposed model consists of two alternate processes, progressive clustering and episodic training. The former generates pseudo-labeled training examples for constructing episodic tasks; and the later trains the few-shot learner using the generated episodic tasks which further optimizes the feature representations of data. The two processes facilitate each other, and eventually produce a high quality few-shot learner. In our experiments, our model achieves good generalization performance in a variety of downstream few-shot learning tasks on Omniglot and MiniImageNet. We also construct a new few-shot person re-identification dataset FS-Market1501 to demonstrate the feasibility of our model to a real-world application.
journal_name
Front Comput Neuroscijournal_title
Frontiers in computational neuroscienceauthors
Ji Z,Zou X,Huang T,Wu Sdoi
10.3389/fncom.2020.00083subject
Has Abstractpub_date
2020-10-14 00:00:00pages
83issn
1662-5188journal_volume
14pub_type
杂志文章abstract::Persistent activity observed during delayed-response tasks for spatial working memory (Funahashi et al., 1989) has commonly been modeled by recurrent networks whose dynamics is described as a bump attractor (Compte et al., 2000). We examine the effects of interareal architecture on the dynamics of bump attractors in s...
journal_title:Frontiers in computational neuroscience
pub_type: 杂志文章
doi:10.3389/fncom.2013.00082
更新日期:2013-07-01 00:00:00
abstract::In this article, we describe and analyze the chaotic behavior of a conductance-based neuronal bursting model. This is a model with a reduced number of variables, yet it retains biophysical plausibility. Inspired by the activity of cold thermoreceptors, the model contains a persistent Sodium current, a Calcium-activate...
journal_title:Frontiers in computational neuroscience
pub_type: 杂志文章
doi:10.3389/fncom.2017.00012
更新日期:2017-03-10 00:00:00
abstract::Modern machine learning is based on powerful algorithms running on digital computing platforms and there is great interest in accelerating the learning process and making it more energy efficient. In this paper we present a fully autonomous probabilistic circuit for fast and efficient learning that makes no use of dig...
journal_title:Frontiers in computational neuroscience
pub_type: 杂志文章
doi:10.3389/fncom.2020.00014
更新日期:2020-02-25 00:00:00
abstract::Neuronal networks exhibit a wide diversity of structures, which contributes to the diversity of the dynamics therein. The presented work applies an information theoretic framework to simultaneously analyze structure and dynamics in neuronal networks. Information diversity within the structure and dynamics of a neurona...
journal_title:Frontiers in computational neuroscience
pub_type: 杂志文章
doi:10.3389/fncom.2011.00026
更新日期:2011-06-01 00:00:00
abstract::Probabilistic models of decision making under various forms of uncertainty have been applied in recent years to numerous behavioral and model-based fMRI studies. These studies were highly successful in enabling a better understanding of behavior and delineating the functional properties of brain areas involved in deci...
journal_title:Frontiers in computational neuroscience
pub_type: 杂志文章
doi:10.3389/fncom.2016.00033
更新日期:2016-04-20 00:00:00
abstract::The generation of pain signals from primary afferent neurons is explained by a labeled-line code. However, this notion cannot apply in a simple way to cutaneous C-fibers, which carry signals from a variety of receptors that respond to various stimuli including agonist chemicals. To represent the discharge patterns of ...
journal_title:Frontiers in computational neuroscience
pub_type: 杂志文章
doi:10.3389/fncom.2016.00118
更新日期:2016-11-18 00:00:00
abstract::Synaptic transmission is both history-dependent and stochastic, resulting in varying responses to presentations of the same presynaptic stimulus. This complicates attempts to infer synaptic parameters and has led to the proposal of a number of different strategies for their quantification. Recently Bayesian approaches...
journal_title:Frontiers in computational neuroscience
pub_type: 杂志文章
doi:10.3389/fncom.2016.00116
更新日期:2016-11-25 00:00:00
abstract::Often we need to perform tasks in an environment that changes stochastically. In these situations it is important to learn the statistics of sequences of events in order to predict the future and the outcome of our actions. The statistical description of many of these sequences can be reduced to the set of probabiliti...
journal_title:Frontiers in computational neuroscience
pub_type: 杂志文章
doi:10.3389/fncom.2013.00032
更新日期:2013-04-12 00:00:00
abstract::Predictive coding hypothesizes that the brain explicitly infers upcoming sensory input to establish a coherent representation of the world. Although it is becoming generally accepted, it is not clear on which level spiking neural networks may implement predictive coding and what function their connectivity may have. W...
journal_title:Frontiers in computational neuroscience
pub_type: 杂志文章
doi:10.3389/fncom.2013.00112
更新日期:2013-09-17 00:00:00
abstract::The cerebellum is known to play a critical role in learning relevant patterns of activity for adaptive motor control, but the underlying network mechanisms are only partly understood. The classical long-term synaptic plasticity between parallel fibers (PFs) and Purkinje cells (PCs), which is driven by the inferior oli...
journal_title:Frontiers in computational neuroscience
pub_type: 杂志文章,评审
doi:10.3389/fncom.2014.00097
更新日期:2014-08-15 00:00:00
abstract::The extent to which groups of neurons exhibit higher-order correlations in their spiking activity is a controversial issue in current brain research. A major difficulty is that currently available tools for the analysis of massively parallel spike trains (N >10) for higher-order correlations typically require vast sam...
journal_title:Frontiers in computational neuroscience
pub_type: 杂志文章
doi:10.3389/fncom.2010.00016
更新日期:2010-07-02 00:00:00
abstract::In order to be able to examine the extracellular potential's influence on network activity and to better understand dipole properties of the extracellular potential, we present and analyze a three-dimensional formulation of the cable equation which facilitates numeric simulations. When the neuron's intra- and extracel...
journal_title:Frontiers in computational neuroscience
pub_type: 杂志文章
doi:10.3389/fncom.2015.00094
更新日期:2015-07-17 00:00:00
abstract::The study of sensory signaling in the visual cortex has been greatly advanced by the recording of neural activity simultaneously with the performance of a specific psychophysical task. Individual nerve cells may also increase their firing leading up to the particular choice or decision made on a single psychophysical ...
journal_title:Frontiers in computational neuroscience
pub_type: 杂志文章
doi:10.3389/fncom.2013.00115
更新日期:2013-08-13 00:00:00
abstract::Neuronal networks in rodent barrel cortex are characterized by stable low baseline firing rates. However, they are sensitive to the action potentials of single neurons as suggested by recent single-cell stimulation experiments that reported quantifiable behavioral responses in response to short spike trains elicited i...
journal_title:Frontiers in computational neuroscience
pub_type: 杂志文章
doi:10.3389/fncom.2013.00156
更新日期:2013-11-07 00:00:00
abstract::Introduction: The early and therapy-specific prediction of treatment success in major depressive disorder is of paramount importance due to high lifetime prevalence, and heterogeneity of response to standard medication and symptom expression. Hence, this study assessed the predictability of long-term antidepressant ef...
journal_title:Frontiers in computational neuroscience
pub_type: 杂志文章
doi:10.3389/fncom.2020.554186
更新日期:2020-10-06 00:00:00
abstract::Neuron classification is an important component in analyzing network structure and quantifying the effect of neuron topology on signal processing. Current quantification and classification approaches rely on morphology projection onto lower-dimensional spaces. In this paper a 3D visualization and quantification tool i...
journal_title:Frontiers in computational neuroscience
pub_type: 杂志文章
doi:10.3389/fncom.2020.00042
更新日期:2020-06-26 00:00:00
abstract::Animals try to make sense of sensory information from multiple modalities by categorizing them into perceptions of individual or multiple external objects or internal concepts. For example, the brain constructs sensory, spatial representations of the locations of visual and auditory stimuli in the visual and auditory ...
journal_title:Frontiers in computational neuroscience
pub_type: 杂志文章
doi:10.3389/fncom.2016.00062
更新日期:2016-06-23 00:00:00
abstract::Brain computer interfaces allow users to preform various tasks using only the electrical activity of the brain. BCI applications often present the user a set of stimuli and record the corresponding electrical response. The BCI algorithm will then have to decode the acquired brain response and perform the desired task....
journal_title:Frontiers in computational neuroscience
pub_type: 杂志文章
doi:10.3389/fncom.2016.00130
更新日期:2016-12-20 00:00:00
abstract::Background: Convolution neural networks (CNN) is increasingly used in computer science and finds more and more applications in different fields. However, analyzing brain network with CNN is not trivial, due to the non-Euclidean characteristics of brain network built by graph theory. Method: To address this problem, we...
journal_title:Frontiers in computational neuroscience
pub_type: 杂志文章
doi:10.3389/fncom.2018.00095
更新日期:2018-12-10 00:00:00
abstract::We do not claim that the brain is completely deterministic, and we agree that noise may be beneficial in some cases. But we suggest that neuronal variability may be often overestimated, due to uncontrolled internal variables, and/or the use of inappropriate reference times. These ideas are not new, but should be re-ex...
journal_title:Frontiers in computational neuroscience
pub_type: 杂志文章
doi:10.3389/fncom.2013.00007
更新日期:2013-02-25 00:00:00
abstract::A vast amount of information about the external world continuously flows into the brain, whereas its capacity to process such information is limited. Attention enables the brain to allocate its resources of information processing to selected sensory inputs for reducing its computational load, and effects of attention ...
journal_title:Frontiers in computational neuroscience
pub_type: 杂志文章
doi:10.3389/fncom.2011.00031
更新日期:2011-07-08 00:00:00
abstract::Purpose: This study is to exam self-esteem related brain morphometry on brain magnetic resonance (MR) images using multilevel-features-based classification method. Method: The multilevel region of interest (ROI) features consist of two types of features: (i) ROI features, which include gray matter volume, white matter...
journal_title:Frontiers in computational neuroscience
pub_type: 杂志文章
doi:10.3389/fncom.2017.00037
更新日期:2017-05-22 00:00:00
abstract::Neuromodulatory inputs from brainstem systems modulate the normal function of spinal motoneurons by altering the activation properties of persistent inward currents (PICs) in their dendrites. However, the effect of the PIC on firing outputs also depends on its location in the dendritic tree. To investigate the interac...
journal_title:Frontiers in computational neuroscience
pub_type: 杂志文章
doi:10.3389/fncom.2014.00110
更新日期:2014-09-09 00:00:00
abstract::Over the last decade robotics has attracted a great deal of interest from teachers and researchers as a valuable educational tool from preschool to highschool levels. The implementation of social-support behaviors in robot tutors, in particular in the emotional dimension, can make a significant contribution to learnin...
journal_title:Frontiers in computational neuroscience
pub_type: 杂志文章
doi:10.3389/fncom.2016.00077
更新日期:2016-08-03 00:00:00
abstract::In synapses, calcium is required for modulating synaptic transmission, plasticity, synaptogenesis, and synaptic pruning. The regulation of calcium dynamics within neurons involves cellular mechanisms such as synaptically activated channels and pumps, calcium buffers, and calcium sequestrating organelles. Many experime...
journal_title:Frontiers in computational neuroscience
pub_type: 杂志文章
doi:10.3389/fncom.2018.00058
更新日期:2018-07-27 00:00:00
abstract::A wide range of blind source separation methods have been used in motor control research for the extraction of movement primitives from EMG and kinematic data. Popular examples are principal component analysis (PCA), independent component analysis (ICA), anechoic demixing, and the time-varying synergy model (d'Avella ...
journal_title:Frontiers in computational neuroscience
pub_type: 杂志文章
doi:10.3389/fncom.2013.00185
更新日期:2013-12-20 00:00:00
abstract::In temporal lobe epilepsy (TLE), the variation of chemical receptor expression underlies the basis of neural network activity shifts, resulting in neuronal hyperexcitability and epileptiform discharges. However, dynamical mechanisms involved in the transitions of TLE are not fully understood, because of the neuronal d...
journal_title:Frontiers in computational neuroscience
pub_type: 杂志文章
doi:10.3389/fncom.2017.00061
更新日期:2017-07-11 00:00:00
abstract::Head direction cells fire to signal the direction in which an animal's head is pointing. They are able to track head direction using only internally-derived information (path integration)In this simulation study we investigate the factors that affect path integration accuracy. Specifically, two major limiting factors ...
journal_title:Frontiers in computational neuroscience
pub_type: 杂志文章
doi:10.3389/fncom.2015.00010
更新日期:2015-02-06 00:00:00
abstract::Behavioral studies have shown spatial working memory impairment with aging in several animal species, including humans. Persistent activity of layer 3 pyramidal dorsolateral prefrontal cortex (dlPFC) neurons during delay periods of working memory tasks is important for encoding memory of the stimulus. In vitro studies...
journal_title:Frontiers in computational neuroscience
pub_type: 杂志文章
doi:10.3389/fncom.2019.00089
更新日期:2020-01-17 00:00:00
abstract::We present a phenomenological model of electrically stimulated auditory nerve fibers (ANFs). The model reproduces the probabilistic and temporal properties of the ANF response to both monophasic and biphasic stimuli, in isolation. The main contribution of the model lies in its ability to reproduce statistics of the AN...
journal_title:Frontiers in computational neuroscience
pub_type: 杂志文章
doi:10.3389/fncom.2016.00008
更新日期:2016-02-08 00:00:00