This special issue is on the theory of neural networks, deep learning, and reinforcement learning in addition to their applications in engineering, including but not limited to representation models, computational biology, automatic speech recognition, image recognition, visual art processing, drug discovery and toxicology, customer relationship management, recommendation systems, medical Image Analysis, mobile advertising, image restoration, financial fraud detection, bioinformatics, molecular dynamics, coarse-graining, natural language processing, etc. Although the main focus of this special issue is on neural network, deep learning, and reinforcement learning, it also includes other machine learning topics including but not limited to decision trees, support vector machines, Bayesian models, Genetic algorithms and their applications in supervised and semi-supervised learning, unsupervised learning, feature learning, anomaly detection, sparse dictionary learning, association rules, fairness in learning, prediction models, regression, online algorithms, ranking algorithms, recommendation systems, Bayesian inference, Bayesian prediction, hypothesis learning, risk minimization, regularization and stability, multi-class clustering, Bayesian SVM, evolutionary algorithms, and stochastic optimization. All researchers in the fields of electrical and computer engineering, computer science, mathematics, physics, civil engineering, biotechnology, mechanical engineering, chemistry, biology, medical, humanities, agriculture, horticulture, forestry, animation and multimedia are encouraged to submit a paper at this special issue as long as they take advantage of neural networks, deep learning, reinforcement learning, and any other machine learning tools in their papers.

Aims and Scope:

1. Neural Networks
2. Deep Learning
3. Machine Learning
4. Statistical Learning
5. Artificial Intelligence
6. Deep Neural Networks