Label-activating framework for zero-shot learning
Existing zero-shot learning (ZSL) models usually learn mappings between visual space and semantic space. However, few of them take the label information into account. Indirect Attribute Prediction (IAP) learns the posterior probability ...
Centralized/decentralized event-triggered pinning synchronization of stochastic coupled networks with noise and incomplete transitional rate
This paper studies the synchronous problem of Markovian switching complex networks associated with partly unknown transitional rates, stochastic noise, and randomly coupling strength. In order to achieve the synchronization for these ...
Modeling place cells and grid cells in multi-compartment environments: Entorhinal–hippocampal loop as a multisensory integration circuit
Hippocampal place cells and entorhinal grid cells are thought to form a representation of space by integrating internal and external sensory cues. Experimental data show that different subsets of place cells are controlled by vision, ...
Spiking Neural Networks and online learning: An overview and perspectives
Applications that generate huge amounts of data in the form of fast streams are becoming increasingly prevalent, being therefore necessary to learn in an online manner. These conditions usually impose memory and processing time ...
Sliding mode control of neural networks via continuous or periodic sampling event-triggering algorithm
This paper presents the theoretical results on sliding mode control (SMC) of neural networks via continuous or periodic sampling event-triggered algorithm. Firstly, SMC with continuous sampling event-triggered scheme is developed and ...
Operation-aware Neural Networks for user response prediction
User response prediction makes a crucial contribution to the rapid development of online advertising system and recommendation system. The importance of learning feature interactions has been emphasized by many works. Many deep models ...
An analysis of training and generalization errors in shallow and deep networks
This paper is motivated by an open problem around deep networks, namely, the apparent absence of over-fitting despite large over-parametrization which allows perfect fitting of the training data. In this paper, we analyze this ...
Event-triggered passivity and synchronization of delayed multiple-weighted coupled reaction–diffusion neural networks with non-identical nodes
This paper solves the event-triggered passivity and synchronization problems for delayed multiple-weighted coupled reaction–diffusion neural networks (DMWCRDNNs) composed of non-identical nodes with and without parameter uncertainties. ...
Embedding topological features into convolutional neural network salient object detection
Salient object detection can be applied as a critical preprocessing step in many computer vision tasks. Recent studies of salient object detection mainly employed convolutional neural networks (CNNs) for mining high-level semantic ...
Interfering with a memory without erasing its trace
Previous research has shown that performance of a novice skill can be easily interfered with by subsequent training of another skill. We address the open questions whether extensively trained skills show the same vulnerability to ...
Highlights
- Skill acquisition in novices can be interfered with by training on another skill.
A biologically plausible supervised learning method for spiking neural networks using the symmetric STDP rule
Spiking neural networks (SNNs) possess energy-efficient potential due to event-based computation. However, supervised training of SNNs remains a challenge as spike activities are non-differentiable. Previous SNNs training methods can ...
Integrating joint feature selection into subspace learning: A formulation of 2DPCA for outliers robust feature selection
Since the principal component analysis and its variants are sensitive to outliers that affect their performance and applicability in real world, several variants have been proposed to improve the robustness. However, most of the ...
Synchronization in an array of coupled neural networks with delayed impulses: Average impulsive delay method
In the paper, synchronization of coupled neural networks with delayed impulses is investigated. In order to overcome the difficulty that time delays can be flexible and even larger than impulsive interval, we propose a new method of ...
Highlights
- We propose a new method of average impulsive delay (AID).
- Some unified ...