Deep learning and machine learning are the state-of-the-art at providing models, methods, tools and techniques for developing autonomous and intelligent systems which can revolutionize industrial and commercial applications in various fields such as online commerce, intelligent transportation, healthcare and medicine, security, manufacturing, education, games, and various other industrial applications. Google, for example, exploits the techniques of deep learning in voice and image recognition applications, while Amazon uses such techniques in helping customers in their online purchase decisions.

The International Conference on Deep Learning and Machine Learning in Emerging Applications (Deep-ML) provides a leading forum for researchers, developers, practitioners, and professional from public sectors and industries in order to meet and share latest solutions and ideas in solving cutting edge problems in modern information society and economy.

The conference comprises a set of tracks that focus on specific challenges in deep learning and machine learning and their applications in emerging areas. Topics of interest include, but are not limited to, the following:
Deep and Machine Learning Models and Techniques:
Novel machine and deep learning
Active learning
Incremental learning and online learning
Agent-based learning
Manifold learning
Multi-task learning
Bayesian networks and applications
Case-based reasoning methods
Statistical models and learning
Computational learning
Evolutionary algorithms and learning
Evolutionary neural networks
Fuzzy logic-based learning
Genetic optimization
Clustering, classification and regression
Neural network models and learning
Parallel and distributed learning
Reinforcement learning
Supervised, semi-supervised and unsupervised learning
Tensor Learning Deep and Machine Learning for Big Data Analytics:
Deep/Machine learning based theoretical and computational models
Novel techniques for big data storage and processing
Data analysis, insights and hidden pattern
Data analysis and decision making
Data wrangling, munching and cleaning
Data integration and fusion
Data visualization
Data and information quality, efficiency and scalability
Security threat detection using big data analytics
Visualizing security threats
Enhancing privacy and trust
Data analytics in complex applications – finance, business, healthcare, engineering, medicine, law, transportation, and telecommunication

Deep and Machine Learning for Data Mining and Knowledge:
Data mining in the web and online systems
Multimedia; images and video data mining
Feature extraction and classification
Information retrieval and extraction
Distributed and P2P data search
Sentiment analysis
Mining high velocity data streams
Anomaly detection in streaming data
Mining social media and social networks
Mining sensor and computer networks data
Mining spatial and temporal datasets
Data classification, clustering, and association
Knowledge acquisition and learning
Knowledge representation and reasoning
Knowledge discovery in large datasets

Deep and Machine Learning for Computing and Network Platforms:
Network and communication systems
Software defined networks
Wireless and sensor networks
Internet of Things (IoT)
Cloud Computing
Edge and Fog Computing

Deep and Machine Learning Application Areas:
Bioinformatics and biomedical informatics
Finance, business and retail
Intelligent transportation
Healthcare, medicine and clinical decision support
Computer vision
Human activity recognition
Information retrieval and web search
Cybersecurity
Natural language processing
Recommender systems
Social media and networks

PUBLICATION:

All accepted papers will be included in the conference proceedings which is published by Springer in the Lecture Notes in Artificial Intelligence (LNAI) - subseries of Lecture Notes in Computer Science (LNCS)(pending approval). For each accepted paper, at least one author must register for the conference and present the paper.
Authors of selected papers will be invited to submit an extended version of their papers for a special issues in international journals (tba).