We accept files in .docx/.doc/.pdf/Latex Pdf format - as per the call for papers schedule.
Papers should be thoroughly checked and proofread before submission. After you have submitted your article you are unable to make any changes to it during the refereeing process—although if accepted, you will have a chance to make minor revisions after refereeing and before the final submission of your paper.

Paper content must be original and relevant to one of the many conference topics.
Authors are required to ensure accuracy of quotations, citations, diagrams, maps, and tables.
Figures and tables need to be placed where they are to appear in the text and must be clear and easy to view.
Papers must follow format according to the template which will be sent to accepted papers.

Machine learning 
Supervised learning 
    Ranking 
    Supervised learning by classification 
    Supervised learning by regression 
    Structured outputs 
    Cost-sensitive learning 
Unsupervised learning 
    Cluster analysis 
    Anomaly detection 
    Mixture modeling 
    Topic modeling 
    Source separation 
    Motif discovery 
    Dimensionality reduction and manifold learning 
Reinforcement learning 
    Sequential decision making 
    Inverse reinforcement learning 
    Apprenticeship learning 
    Multi-agent reinforcement learning 
    Adversarial learning 
Multi-task learning 
    Transfer learning 
    Lifelong machine learning 
    Learning under covariate shift 
Learning settings 
    Batch learning 
    Online learning settings 
    Learning from demonstrations 
    Learning from critiques 
    Learning from implicit feedback 
    Active learning settings 
    Semi-supervised learning settings 
Machine learning approaches 
    Classification and regression trees 
    Kernel methods 
        Support vector machines 
            Gaussian processes 
            Neural networks 
    Logical and relational learning 
    Inductive logic learning 
    Statistical relational learning 
    Learning in probabilistic graphical models 
        Maximum likelihood modeling 
        Maximum entropy modeling 
        Maximum a posteriori modeling 
        Mixture models 
        Latent variable models 
        Bayesian network models 
    Learning linear models 
        Perceptron algorithm 
    Factorization methods 
        Non-negative matrix factorization 
            Factor analysis 
            Principal component analysis 
            Canonical correlation analysis 
            Latent Dirichlet allocation 
Rule learning 
Instance-based learning 
Markov decision processes 
Partially-observable Markov decision processes 
Stochastic games 
Learning latent representations 
    Deep belief networks 
Bio-inspired approaches 
    Artificial life 
    Evolvable hardware 
    Genetic algorithms 
    Genetic programming 
    Evolutionary robotics 
    Generative and developmental approaches 
Machine learning algorithms 
    Dynamic programming for Markov decision processes 
    Value iteration 
    Q-learning 
    Policy iteration 
    Temporal difference learning 
    Approximate dynamic programming methods 
    Ensemble methods 
    Boosting 
    Bagging 
    Spectral methods 
    Feature selection 
    Regularization 
    Cross-validation