AIMC Journal:
IEEE transactions on neural networks and learning systems

Showing 611 to 620 of 817 articles

Early Expression Detection via Online Multi-Instance Learning With Nonlinear Extension.

IEEE transactions on neural networks and learning systems
Video-based facial expression recognition has received substantial attention over the past decade, while early expression detection (EED) is still a relatively new and challenging problem. The goal of EED is to identify an expression as quickly as po...

Hypergraph-Induced Convolutional Networks for Visual Classification.

IEEE transactions on neural networks and learning systems
At present, convolutional neural networks (CNNs) have become popular in visual classification tasks because of their superior performance. However, CNN-based methods do not consider the correlation of visual data to be classified. Recently, graph con...

Multiview Multitask Gaze Estimation With Deep Convolutional Neural Networks.

IEEE transactions on neural networks and learning systems
Gaze estimation, which aims to predict gaze points with given eye images, is an important task in computer vision because of its applications in human visual attention understanding. Many existing methods are based on a single camera, and most of the...

A Discrete-Time Projection Neural Network for Sparse Signal Reconstruction With Application to Face Recognition.

IEEE transactions on neural networks and learning systems
This paper deals with sparse signal reconstruction by designing a discrete-time projection neural network. Sparse signal reconstruction can be converted into an L -minimization problem, which can also be changed into the unconstrained basis pursuit d...

Enhanced Robot Speech Recognition Using Biomimetic Binaural Sound Source Localization.

IEEE transactions on neural networks and learning systems
Inspired by the behavior of humans talking in noisy environments, we propose an embodied embedded cognition approach to improve automatic speech recognition (ASR) systems for robots in challenging environments, such as with ego noise, using binaural ...

A Highly Effective and Robust Membrane Potential-Driven Supervised Learning Method for Spiking Neurons.

IEEE transactions on neural networks and learning systems
Spiking neurons are becoming increasingly popular owing to their biological plausibility and promising computational properties. Unlike traditional rate-based neural models, spiking neurons encode information in the temporal patterns of the transmitt...

Adaptive Neural Control of Pure-Feedback Nonlinear Systems With Event-Triggered Communications.

IEEE transactions on neural networks and learning systems
This paper is concerned with the adaptive event-triggered control problem for a class of pure-feedback nonlinear systems. Unlike the existing results where the control execution is periodic, the new proposed scheme updates the controller and the neur...

A New Correntropy-Based Conjugate Gradient Backpropagation Algorithm for Improving Training in Neural Networks.

IEEE transactions on neural networks and learning systems
Mean square error (MSE) is the most prominent criterion in training neural networks and has been employed in numerous learning problems. In this paper, we suggest a group of novel robust information theoretic backpropagation (BP) methods, as correntr...

Behavioral Learning in a Cognitive Neuromorphic Robot: An Integrative Approach.

IEEE transactions on neural networks and learning systems
We present here a learning system using the iCub humanoid robot and the SpiNNaker neuromorphic chip to solve the real-world task of object-specific attention. Integrating spiking neural networks with robots introduces considerable complexity for ques...

Dynamical and Static Multisynchronization of Coupled Multistable Neural Networks via Impulsive Control.

IEEE transactions on neural networks and learning systems
This paper investigates the dynamical multisynchronization and static multisynchronization problem for delayed coupled multistable neural networks with fixed and switching topologies. To begin with, a class of activation functions as well as several ...