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 Neural Networks with Cloud Computing
Submission Date: 2022-03-15

To perform high performance computing in terms of speed and memory, training and executing DNNs are increasingly performed using cloud platforms. Training with reasonable time can be performed in cloud machine learning platforms such as AWS Deep Learning and Google Colab, which have huge computing and memory resources. Executions at high speeds can also be performed by implementing the DNNs in the cloud with lower latency networks. Edge computing is necessary, as we need fast DNN execution time on the edge to have a quick responses from the DNNs. Integration of deep learning and cloud computing is a growing and popular area currently. A cloud based DNN can be developed if the cloud limitations are overcome and advantages of cloud resources are effectively used to train or execute the DNNs.

This special issue aims to solicit original papers describing innovative techniques that develop DNNs based on cloud computing. Researchers are welcome to submit research, technical, review, survey, or vision articles which contribute on the algorithmic development, implementations, or real applications of integrations of DNNs and cloud computing. Topics include, but are not limited to:

● Deep learning approaches using cloud computing services
● Low-power DNN engines in the cloud
● Energy efficiency of implementing DNNs in the cloud
● Implementation of DNNs using mobile cloud computing
● Parallel computing to train DNNs using cloud services
● Optimization of computational resources for training DNNs in the cloud
● Low-cost and powerful GPUs in cloud for training DNNs
● Memory allocations in cloud for deep learning
● Cloud data streaming for deep learning
● High resolution video processing using DNNs in the cloud
● Real-time metrics for measuring DNN performance, accuracy, and complexity in the cloud
● Training data privacy such as medical data, finance data in the cloud
● Tools and libraries in the cloud for deep learning
● Optimization of DNN configurations and architectures in the cloud
● Implementation of hybrid DNNs/compressed DNNs in the cloud
● Evolutionary computation for DNNs using the cloud
● DNNs for Knowledge Graph Embeddings using the cloud
● Implementing deep learning in the cloud for big data analysis such as business intelligence, e-commences, bioinformatics, weather forecasting, smart surveillance, traffic flow forecasting, autonomous driving, climate change forecasting, etc.