Neurocomputing publishes articles describing recent fundamental contributions in the field of neurocomputing. Neurocomputing theory, practice and applications are the essential topics being covered.

Neurocomputing welcomes theoretical contributions aimed at winning further understanding of neural networks and learning systems, including, but not restricted to, architectures, learning methods, analysis of network dynamics, theories of learning, self-organization, biological neural network modelling, sensorimotor transformations and interdisciplinary topics with artificial intelligence, artificial life, cognitive science, computational learning theory, fuzzy logic, genetic algorithms, information theory, machine learning, neurobiology and pattern recognition.

Neurocomputing covers practical aspects with contributions on advances in hardware and software development environments for neurocomputing, including, but not restricted to, simulation software environments, emulation hardware architectures, models of concurrent computation, neurocomputers, and neurochips (digital, analog, optical, and biodevices).

Neurocomputing reports on applications in different fields, including, but not restricted to, signal processing, speech processing, image processing, computer vision, control, robotics, optimization, scheduling, resource allocation and financial forecasting.

Neurocomputing publishes reviews of literature about neurocomputing and affine fields.

Neurocomputing reports on meetings, including, but not restricted to, conferences, workshops and seminars.

Neurocomputing reports on functionality/availability of software, on comparative assessments, and on discussions of neurocomputing software issues.

Now also including: Neurocomputing Letters - for the rapid publication of special short communications.

Special Issue on Deep Learning for Medical Image Computing
Submission Date: 2019-12-01

Deep learning is one of the most important breakthroughs in the field of artificial intelligence over the last decade. It has achieved great success in different tasks in computer vision and image processing. Methods and models on medical image analysis also benefit from the powerful representation learning capability of deep learning techniques. Not only there has been a constantly growing flow of related research papers, but also substantial progress has been achieved in real-world applications such as radiotherapy planning, histological image understanding and retina image recognition.

While substantial progress has been achieved in medical image analysis with deep learning, many issues still remain and new problems emerge. For instance, the scalability of 3D deep networks to handle thin-layer CT images, the limited training samples of medical images compared with other image understanding tasks, the significant class imbalance of many medical classification problems, noisy and weakly supervisions for training deep learning models from medical reports. The accuracy and efficiency of deep learning models for medical image analysis also see large room for improvement.

This special issue presents a great platform to make a definitive statement about the state of the art by providing a significant collective contribution to this emerging field of study. Specifically, we aim to solicit original contributions that: (1) present state-of-the-art deep learning methods for medical image analysis; (2) develop novel methods and applications; (3) survey the recent progress in this area; and (4) establish benchmark datasets.

Topics of Interest:

The topics of interest include (but not limited to):

-- Theoretical analysis of deep learning models for medical image analysis
--Evaluation of deep learning models for medical image analysis
--New object functions and formulations for medical image analysis
--New network structures and training schema for medical image analysis
--Deep learning methods for medical image classification
--Deep learning methods for medical image segmentation
--Deep learning methods for detection from medical images
--Deep learning methods for medical image registration
--Deep learning methods for 4D medical image sequence analysis
--Generative models for medical images
--Deep adversarial learning for medical image analysis
--Weakly or semi-supervised deep learning for medical image analysis

Special Issue on Deep Understanding of Big Geospatial Data for Self-Driving Cars
Submission Date: 2019-12-31

A self-driving car means that a car is capable of sensing its environment and moving with little or no human input. Compared to traditional human-driving cars, self-driving cars have the potential to reduce traffic accidents, traffic congestions, and fuel consumption. There is no doubt that the self-driving is the future direction of intelligent transportation.

Big geospatial data understanding plays a fundamental role in self-driving cars, which is helpful in acquiring the patterns of driving/travel behavior, human mobility, and traffic flow, and in sensing the environment and giving a traffic-aware navigation. Generally, geospatial data include road network data, digital elevation model (DEM) data, vehicle and human trajectory data, traffic flow data, traffic accident data, traffic satellite image data, and location-based social media data. The storage and deep understanding of geospatial data face many challenges. In this special issue, we invite researchers to address the challenges on deep understanding of big geospatial data for self-driving cars.

The list of possible topics include, but not limited to:

Deep understanding of big geospatial data
Geospatial data preprocessing, including data cleaning, feature selection and extraction, data clustering, and map-matching.
Distributed and parallel computing for big geospatial data
Deep learning/reinforcement learning/federated learning on big geospatial data
Big geospatial data mining
Geospatial data driven self-driving applications
Deep understanding of traffic satellite images
Driving behavior analytics and prediction
Traffic flow/human mobility detection and prediction
Traffic-aware routing and navigation
Spatial Crowdsourcing

Special Issue on Advances of Neurocomputing for Smart Cities
Submission Date: 2019-12-31

In recent years, urban environments have been reimagined as "Smart cities of the future" with the intelligent computation capacity to monitor, learn about, and adapt to the people that inhabit them. Innovations in information and communication technologies have made cities smarter at being able to run their systems more efficiently and effectively, connecting them with their residents and communities. The word "Smart" is interchangeable with intelligent, digital, or ubiquitous, to connect a wide range of city- and citizen-related issues based on intelligent technologies.

With the resurgence of deep learning architectures and learning methods, neurocomputing has been applied to a variety of disciplines and proved highly successful in a vast class of intelligent applications cross many domains, e.g., computer vision, speech recognition, text understanding, natural language processing, Game AI, and many more. Some initial attempts of applying neurocomputing on smart cities can be found in the literature. However, many challenging research problems, such as the architecture of neurocomputing, neural network modelling, accurate and efficient learning methods, and neural network based automatic scheduling for smart cities remain unsolved well. This special issue intends to collect and disseminate latest discoveries, researches and results on Neurocomputing for smart cities.

The list of possible topics includes, but is not limited to:

Architecture, Algorithm for Intelligent Computing on Smart Cites
Neural Networks based Algorithms and Applications for Smart Cites
Machine Learning and Artificial Intelligence for Smart Cites
Neural network modelling for Smart Cites
Urban Planning/Scheduling on Neural Networks for Smart Cities
High-performance Computing Architectures for Neurocomputing on Smart Cities
Internet of Things (IoT) based on Neurocomputing for Smart Cities

Special Issue on Human Visual Saliency and Artificial Neural Attention in Deep Learning
Submission Date: 2020-01-10

Human visual system canprocess large amounts of visual information (108-109bits per second) in parallel. Such astonishing ability is based on the visual attention mechanism which allows human beings to selectively attend to the most informative and characteristic parts of a visual stimulus rather than the whole scene. Modeling visual saliency is a long-term core topic in cognitive psychology and computer vision community. Further, understanding human gaze behavior during social scenes is essential for understanding Human-Human Interactions (HHIs) and enabling effective and natural Human-Robot Interactions (HRIs). In addition, the selective mechanism of human visual system inspires the development of differentiable neural attention in neural networks. Neural networks with attention mechanism are able to automatically learn to selectively focus on sections of input, which have shown wide success in many neural language processing and mainstream computer vision tasks, such asneural machine translation, sentence summarization, image caption generation, visual question answering, and action recognition. The visual attention mechanism also boosts biologically-inspired object recognition, including salient object detection, object segmentation, and object classification.

The list of possible topics includes, but is not limited to:

Visual attention prediction during static/dynamic scenes
Computational models for saliency/co-saliency detection in images/videos
Computational models for social gaze, co-attention and gaze-following behavior
Gaze-assistant Human-Robotics Interaction (HRI) algorithms and gaze-based Human-Human Interaction (HHI) models
Neural attention based NPL applications (e.g., neural machine translation, sentence summarization, etc)
Approaches for attention-guided object recognition, such as object classification, object segmentation and object detection.
Visual saliency for various applications (e.g., object tracking, human-machine interaction, and automatic photo editing, etc.)
Artificial attention and multi-modal attention based applications (e.g., network knowledge distillation, network visualization, image captioning, and visual question answering, etc.)
New benchmark datasets and evaluation metrics related to the aforementioned topics

Special Issue on Deep Learning with Small Samples
Submission Date: 2020-04-15

In machine learning and computer vision fields, due to the rapid development of deep learning, recent years have witnessed breakthroughs for large-sample classification tasks. However, it remains a persistent challenge to learn a deep neural network with good generalizability from only a small number of training samples. In fact, humans can easily learn the concept of a class from a small amount of data rather than from millions of data. Moreover, many types of real-world data are small in quantity and are expensive to collect and label. Motivated by this fact, research on deep learning with small samples becomes more and more prevalent in the communities of machine learning and computer vision, for example, researches focusing on one-shot classification, few-shot classification, as well as classification with small training samples.

Recently, deep small-sample learning has achieved promising performance in certain small-sample problems, by transferring the "Knowledge" learned from other datasets containing rich labelled data or generating synthetic samples to approximate the distribution of real data. However, many challenging topics remain with small-sample deep leaning techniques, such as data augmentation, feature learning, prior construction, meta-learning, fine tuning, etc. Therefore, the goal of this special issue is to collect and publish the latest developments in various aspects of deep learning with small samples.

The list of possible topics includes, but is not limited to:

Survey/vision/review of deep learning with small samples
Data augmentation methods for small-sample leaning
Feature learning based methods small-sample leaning
Regularization technology of deep model in small-sample leaning
Ensemble learning based methods for small-sample learning
Transfer learning methods for small-sample learning
Semi-supervised learning methods for small-sample learning
Prior based methods for few-shot learning
Meta-leaning based methods for few-shot learning
Fine-tuning based methods for small-sample learning
Theoretical analysis for small-sample learning
Applications of small-sample learning on person re-identification, object recognition, etc.