NIPS 2016 - Thirtieth Annual Conference on Neural Information Processing Systems (NIPS)

Thirtieth Annual Conference on Neural Information Processing Systems (NIPS) is a single-track machine learning and computational neuroscience conference that includes invited talks, demonstrations and oral and poster presentations of refereed papers.
Typical NIPS papers often but not always consist of a mix of algorithmic, theoretical and experimental results, in varying proportions. However, while theoretically grounded arguments are certainly welcome, it is counterproductive to add "decorative maths" whose only purpose is to make the paper look more substantial or even intimidating, without adding relevant insights. Algorithmic contributions should have at least an illustration of how the algorithm can eventually materialize into a machine learning application.
Technical Areas: Papers are solicited in all areas of neural information processing and statistical learning, including, but not limited to:
Neuroscience, cognitive science, and brain imaging: Theoretical and experimental studies of processing and transmission of information in biological neurons and networks, including spike train generation, synaptic modulation, plasticity and adaptation. Neuroimaging, cognitive neuroscience, connectomics, brain mapping, brain segmentation, brain computer interfaces, theoretical, computational, or experimental studies of perception, psychophysics, human or animal learning, memory, reasoning, problem solving, and neuropsychology.
Algorithms and Architectures: Statistical learning algorithms, kernel methods, graphical models, Gaussian processes, Bayesian methods, neural networks, deep learning, dimensionality reduction and manifold learning, hyper-parameter and model selection, combinatorial optimization, relational and structured learning, Markov decision processes, reinforcement Learning, dynamical systems, recurrent networks.
Learning Theory: Models of learning and generalization, regularization and model selection, large deviations and asymptotic analysis, Bayesian learning, spaces of functions and kernels, statistical physics of learning, online learning and competitive analysis, computational complexity, hardness of learning and approximations, statistical theory, control theory, information theory.
Applications: Innovative applications that use machine learning, including systems for time series prediction, bioinformatics, systems biology, text/web analysis, multimedia processing, robotics, natural language processing, decision and control, exploration, planning, navigation, game playing, multi-agent coordination, speech, image, and signal processing, coding, synthesis, denoising, segmentation, source separation, auditory perception, psychoacoustics, other aspects of computer vision, object detection and recognition, motion detection and tracking, visual psychophysics, visual scene analysis and interpretation.
Data, competitions, implementations and software tools: Datasets or data repositories, benchmarks, competitions or challenges and software toolkits.
Dual Submissions Policy: Submissions that are identical (or substantially similar) to versions that have been previously published, or accepted for publication, or that have been submitted in parallel to other conferences are not appropriate for NIPS and violate our dual submission policy. Exceptions to this rule are the following:
Previously published papers by the authors on related topics must be cited (with adequate means of preserving anonymity).
It is acceptable to submit to NIPS 2016 work that has been made available as a technical report (or similar, e.g. in arXiv) without citing it.
The dual-submission rules apply during the whole NIPS review period until the authors have been notified about the decision on their paper.
Demonstrations, Workshops, and Symposia: There is a separate Demonstration track at NIPS. Authors wishing to submit to the Demonstration track should consult the upcoming Call for Demonstrations. There is also a separate Call for Workshops & Symposia.