Conference on Neural Information Processing Systems

Conference on Neural Information Processing Systems
Abbreviation	NeurIPS (formerly NIPS)
Discipline	Machine learning, statistics, artificial intelligence, computational neuroscience
Publication details
History	1987–present
Frequency	Annual
Website	https://neurips.cc/

The Conference and Workshop on Neural Information Processing Systems (NeurIPS, formerly called NIPS) is a machine learning and computational neuroscience conference held every December. The conference is currently a double-track meeting (single-track until 2015) that includes invited talks as well as oral and poster presentations of refereed papers, followed by parallel-track workshops that up to 2013 were held at ski resorts.

History

Machine learning and data mining
Problems Classification Clustering Regression Anomaly detection AutoML Association rules Reinforcement learning Structured prediction Feature engineering Feature learning Online learning Semi-supervised learning Unsupervised learning Learning to rank Grammar induction
Supervised learning (classification • regression) Decision trees Ensembles Bagging Boosting Random forest k-NN Linear regression Naive Bayes Artificial neural networks Logistic regression Perceptron Relevance vector machine (RVM) Support vector machine (SVM)
Clustering BIRCH CURE Hierarchical k-means Expectation–maximization (EM) DBSCAN OPTICS Mean-shift
Dimensionality reduction Factor analysis CCA ICA LDA NMF PCA t-SNE
Structured prediction Graphical models Bayes net Conditional random field Hidden Markov
Anomaly detection k-NN Local outlier factor
Artificial neural networks Autoencoder Deep learning DeepDream Multilayer perceptron RNN LSTM GRU) Restricted Boltzmann machine SOM Convolutional neural network U-Net
Reinforcement learning Q-learning SARSA Temporal difference (TD)
Theory Bias-variance dilemma Computational learning theory Empirical risk minimization Occam learning PAC learning Statistical learning VC theory
Machine-learning venues NIPS ICML ML JMLR ArXiv:cs.LG
Glossary of artificial intelligence Glossary of artificial intelligence
Related articles List of datasets for machine-learning research Outline of machine learning
Machine learning portal

The NIPS meeting was first proposed in 1986 at the annual invitation-only Snowbird Meeting on Neural Networks for Computing organized by The California Institute of Technology and Bell Laboratories. NIPS was designed as a complementary open interdisciplinary meeting for researchers exploring biological and artificial Neural Networks. Reflecting this multidisciplinary approach, NIPS began in 1987 with information theorist Ed Posner as the conference president and learning theorist Yaser Abu-Mostafa and computational neurobiologist James Bower as co-program chairman. Research presented in the early NIPS meetings including a wide range of topics from efforts to solve purely engineering problems to the use of computer models as a tool for understanding biological nervous systems. Since then, the biological and artificial systems research streams have diverged, and recent NIPS proceedings have been dominated by papers on machine learning, artificial intelligence and statistics.

From 1987 until 2000 NIPS was held in Denver, United States. Since then, the conference was held in Vancouver, Canada (2001–2010), Granada, Spain (2011), and Lake Tahoe, United States (2012–2013). In 2014 and 2015, the conference was held in Montreal, Canada, in Barcelona, Spain in 2016, and in Long Beach, United States in 2017. Reflecting its origins at Snowbird, Utah, the meeting was accompanied by workshops organized at a nearby ski resort up until 2013, when it outgrew ski resorts.

The NIPS Conference is organized by the NIPS Foundation, established by Ed Posner in 1987. Terrence Sejnowski has been the president of the NIPS Foundation since 1993, when Posner had a bicycle accident. The board of trustees consists of previous general chairs of the NIPS Conference.

The proceedings from the conferences have been published in book form by Morgan Kaufmann (1987–1993), MIT Press (1994–2004) and Curran Associates (2005–present) under the name Advances in Neural Information Processing Systems.

Name

Conference organizers considered abandoning the NIPS name because of a slang connotation with the word nipples. After a comment period and survey of 2270 conference participants, conference organizers decided to keep the name. Of the survey respondents, 1,881 were men and 294 were women. Of the women, 44% agreed a name change should occur and 40% disagreed. Of the men, 28% agreed a name change should occur and 55% disagreed. However, on November 17th, 2018, the Neural Information Processing Systems Foundation Board of Trustees decided to change the official acronym of the conference from NIPS to NeurIPS.

Topics

Judea Pearl at his poster at the 2013 Conference on Neural Information Processing Systems.

The conference had 5,000 registered participants in 2016 and 8,000 in 2017, making it the largest conference in Artificial Intelligence. Besides machine learning and neuroscience, other fields represented at NIPS include cognitive science, psychology, computer vision, statistical linguistics, and information theory. Although the 'Neural' in the NIPS acronym had become something of a historical relic, the resurgence of deep learning in neural networks since 2012, fueled by faster computers and big data, has led to impressive achievement in speech recognition, object recognition in images, image captioning, language translation and world championship performance in the game of Go, based on neural architectures inspired by the hierarchy of areas in the visual cortex (ConvNet) and reinforcement learning inspired by the basal ganglia (Temporal difference learning).

Named lectures

In addition to invited talks and symposia, NIPS also organizes two named lectureships to recognize distinguished researchers. The NIPS Board introduced the Posner Lectureship in honor of NIPS founder Ed Posner; two Posner Lectures were given each year up to 2015. Past lecturers have included:

• 2017 – John Platt
• 2016 – Yann LeCun
• 2015 – Zoubin Ghahramani and Vladimir Vapnik
• 2014 – Michael Kearns and John Hopfield
• 2013 – Daphne Koller and Peter Dayan
• 2012 – Thomas Dietterich and Terry Sejnowski
• 2011 – Rich Sutton and Bernhard Scholkopf
• 2010 – Josh Tenenbaum and Michael I. Jordan

In 2015, the NIPS Board introduced the Breiman Lectureship to highlight work in statistics relevant to conference topics. The lectureship was named for statistician Leo Breiman, who served on the NIPS Board from 1994 to 2005. Past lecturers have included:

• 2017 - Yee Whye Teh
• 2016 – Susan Holmes
• 2015 – Robert Tibshirani

The NIPS experiment

In NIPS 2014, the program chairs duplicated 10% of all submissions and sent them through separate reviewers to evaluate randomness in the reviewing process. Several researchers interpreted the result. Regarding whether the decision in NIPS is completely random or not, John Langford writes: "Clearly not—a purely random decision would have arbitrariness of ~78%. It is, however, quite notable that 60% is much closer to 78% than 0%." He concludes that the result of the reviewing process is mostly arbitrary.

Editions

Past editions:

• 1987 → 2000: Denver, Colorado, United States
• 2001 → 2010: Vancouver, British Columbia, Canada
• 2011: Granada, Spain, EU
• 2012 and 2013: Stateline, Nevada, United States
• 2014 and 2015: Montréal, Quebec, Canada
• 2016: Barcelona, Spain, EU
• 2017: Long Beach, California, United States
• 2018: Montréal, Quebec, Canada

Future editions:

• 2019 and 2020: Vancouver, British Columbia, Canada

See also

• COSYNE
• ICML
• CIBB
• ICLR

External links

• http://neurips.cc/
• NIPS proceedings
• NIPS 2011 video lectures
• NIPS 2012 video lectures
• Video Journal of Machine Learning Abstracts – Volume 3