Manuscript Topics

Nowadays, a huge amount of training data comes from powerful computers. On the other hand, the computational power of machines is increased over the years. The training data are used for training neural networks through suitable training algorithms. Thus, suitable Deep Learning based approaches are developed to solve specific problems. However, the related literature is still based on empirical approaches. Moreover, a sound theoretical foundation is largely missing. The aim of this special issue is to enhance the research on deep learning by using a strict mathematical formalism to explain the methods for solving mathematical and/or optimization problems.

This special issue serves as a forum for facilitating and enhancing information sharing among researchers, about the analysis of Mathematical Foundation on Deep Learning and its development for solving specific problems.

Topics:
Researchers are invited to submit their original and unpublished research work in the following (but not limited to) areas:
• Linear Algebra for Machine Learning
• Multivariate Calculus for Machine Learning
• Probability for Machine Learning
• Statistics for Machine Learning
• Convolutional Networks
• Auto Encoders
• Deep Belief Networks
• Recurrent Neural Networks
• Long Short Term Memory
• Deep and restricted Boltzmann Machines
• Deep Reinforcement Learning
• New machine learning algorithms
• New optimization techniques
• Distributed machine learning systems and architectures
• New applications on real-time/big data analytics
• Intelligent applications
• Quantum machine learning
• Data and code integration

Instructions for authors
https://www.aimspress.com/mbe/news/solo-detail/instructionsforauthors
Please submit your manuscript to online submission system
https://aimspress.jams.pub/