NeuroGenesysThe research we build on.
1,514 papers by other researchers that our work cites, from continual learning and verification to language models, agents and hardware. Each entry links to the paper on arXiv and to where we use it. 301 are cited on published pages of this site; the rest in the research notes behind our studies. Our own papers are in the archive.
- 2015-12arXiv 1512.04906Strategies for Training Large Vocabulary Neural Language Models
Welin Chen, David Grangier, Michael Auli · Language models & NLP
Training neural network language models over large vocabularies is still computationally very costly compared to count-based models such as Kneser-Ney.
- 2015-12arXiv 1512.04922Always Valid Inference: Bringing Sequential Analysis to A/B Testing
Ramesh Johari, Leo Pekelis, David J. Walsh · Statistics & theory
A/B tests are typically analyzed via frequentist p-values and confidence intervals; but these inferences are wholly unreliable if users endogenously choose samples sizes by *continuously monitoring* their tests.
- 2015-11arXiv 1511.06233Towards Open Set Deep Networks
Abhijit Bendale, Terrance Boult · Vision
Deep networks have produced significant gains for various visual recognition problems, leading to high impact academic and commercial applications.
- 2015-11arXiv 1511.06361Order-Embeddings of Images and Language
Ivan Vendrov, Ryan Kiros, Sanja Fidler et al. · Machine learning
Hypernymy, textual entailment, and image captioning can be seen as special cases of a single visual-semantic hierarchy over words, sentences, and images. In this paper we advocate for explicitly modeling the partial order structure of this hierarchy.
- 2015-11arXiv 1511.05641Net2Net: Accelerating Learning via Knowledge Transfer
Tianqi Chen, Ian Goodfellow, Jonathon Shlens · Machine learning
We introduce techniques for rapidly transferring the information stored in one neural net into another neural net. The main purpose is to accelerate the training of a significantly larger neural net.
- 2015-07arXiv 1507.07580Computational principles of biological memory
Marcus K. Benna, Stefano Fusi · Neuroscience & neural computation
Memories are stored, retained, and recollected through complex, coupled processes operating on multiple timescales.
- 2015-06arXiv 1506.01567Classification with many classes: challenges and pluses
Felix Abramovich, Marianna Pensky · Statistics & theory
The objective of the paper is to study accuracy of multi-class classification in high-dimensional setting, where the number of classes is also large ("large , large , small " model).
- 2015-05arXiv 1505.06353The evolutionary origins of hierarchy
Henok Mengistu, Joost Huizinga, Jean-Baptiste Mouret et al. · Neuroscience & neural computation
Hierarchical organization -- the recursive composition of sub-modules -- is ubiquitous in biological networks, including neural, metabolic, ecological, and genetic regulatory networks, and in human-made systems, such as large organizations and the Internet.
- 2015-05arXiv 1505.02463A Survey on Truth Discovery
Yaliang Li, Jing Gao, Chuishi Meng et al. · Retrieval & data
Thanks to information explosion, data for the objects of interest can be collected from increasingly more sources. However, for the same object, there usually exist conflicts among the collected multi-source information.
- 2015-04arXiv 1504.04909Illuminating search spaces by mapping elites
Jean-Baptiste Mouret, Jeff Clune · AI & agents
Many fields use search algorithms, which automatically explore a search space to find high-performing solutions: chemists search through the space of molecules to discover new drugs; engineers search for stronger, cheaper, safer designs, scientists search for models that best explain data, etc.
- 2015-02arXiv 1502.05477Trust Region Policy Optimization
John Schulman, Sergey Levine, Philipp Moritz et al. · Machine learning
We describe an iterative procedure for optimizing policies, with guaranteed monotonic improvement. By making several approximations to the theoretically-justified procedure, we develop a practical algorithm, called Trust Region Policy Optimization (TRPO).
- 2015-02arXiv 1502.03519Knowledge-Based Trust: Estimating the Trustworthiness of Web Sources
Xin Luna Dong, Evgeniy Gabrilovich, Kevin Murphy et al. · Retrieval & data
The quality of web sources has been traditionally evaluated using exogenous signals such as the hyperlink structure of the graph. We propose a new approach that relies on endogenous signals, namely, the correctness of factual information provided by the source.
- 2014-12arXiv 1412.1193New insights and perspectives on the natural gradient method
James Martens · Machine learning
Natural gradient descent is an optimization method traditionally motivated from the perspective of information geometry, and works well for many applications as an alternative to stochastic gradient descent.
- 2014-11arXiv 1411.2664Preserving Statistical Validity in Adaptive Data Analysis
Cynthia Dwork, Vitaly Feldman, Moritz Hardt et al. · Machine learning
A great deal of effort has been devoted to reducing the risk of spurious scientific discoveries, from the use of sophisticated validation techniques, to deep statistical methods for controlling the false discovery rate in multiple hypothesis testing.
- 2014-06arXiv 1406.2938Invention as a Combinatorial Process: Evidence from U.S. Patents
Hyejin Youn, Luis M. A. Bettencourt, Deborah Strumsky et al. · J. R. Soc. Interface 12: 20150272 2015 · Hardware, photonics & physics
Invention has been commonly conceptualized as a search over a space of combinatorial possibilities.
- 2013-12arXiv 1312.4314Learning Factored Representations in a Deep Mixture of Experts
David Eigen, Marc'Aurelio Ranzato, Ilya Sutskever · Machine learning
Mixtures of Experts combine the outputs of several "expert" networks, each of which specializes in a different part of the input space. This is achieved by training a "gating" network that maps each input to a distribution over the experts.
- 2013-08arXiv 1308.3513Hidden Parameter Markov Decision Processes: A Semiparametric Regression Approach for Discovering Latent Task Parametrizations
Finale Doshi-Velez, George Konidaris · Machine learning
Control applications often feature tasks with similar, but not identical, dynamics.
Cited inStudy: Genesys program prior art - 2013-02arXiv 1302.4267Mutation Rules and the Evolution of Sparseness and Modularity in Biological Systems
Tamar Friedlander, Avraham E. Mayo, Tsvi Tlusty et al. · PLoS ONE 8(8): e70444 · Neuroscience & neural computation
Biological systems exhibit two structural features on many levels of organization: sparseness, in which only a small fraction of possible interactions between components actually occur; and modularity - the near decomposability of the system into modules with distinct functionality.
- 2013-01arXiv 1301.5919The hypothesis of urban scaling: formalization, implications and challenges
Luis M. A. Bettencourt, Jose Lobo, Hyejin Youn · Hardware, photonics & physics
There is strong expectation that cities, across time, culture and level of development, share much in common in terms of their form and function.
- 2013-01arXiv 1301.6725Loopy Belief Propagation for Approximate Inference: An Empirical Study
Kevin Murphy, Yair Weiss, Michael I. Jordan · AI & agents
The most dramatic instance OF this IS the near Shannon - limit performance OF Turbo Codes codes whose decoding algorithm IS equivalent TO loopy belief propagation IN a chain - structured Bayesian network.
- 2012-10arXiv 1212.2447Bayesian Hierarchical Mixtures of Experts
Christopher M. Bishop, Markus Svensen · Machine learning
The Hierarchical Mixture of Experts (HME) is a well-known tree-based model for regression and classification, based on soft probabilistic splits. In its original formulation it was trained by maximum likelihood, and is therefore prone to over-fitting.
- 2012-10arXiv 1210.5215The scaling of human interactions with city size
Markus Schläpfer, Luis M. A. Bettencourt, Sebastian Grauwin et al. · J. R. Soc. Interface 11 (98), 20130789 (2014) · Hardware, photonics & physics
The size of cities is known to play a fundamental role in social and economic life. Yet, its relation to the structure of the underlying network of human interactions has not been investigated empirically in detail.
- 2012-08arXiv 1208.6430The Lyapunov exponent of products of random matrices close to the identity
A. Comtet, J. M. Luck, C. Texier et al. · J. Stat. Phys. 150, 13-65 (2013) · Statistics & theory
We study products of arbitrary random real matrices that are close to the identity matrix. Using the Iwasawa decomposition of , we identify a continuum regime where the mean values and the covariances of the three Iwasawa parameters are simultaneously small.
- 2012-07arXiv 1207.2743The evolutionary origins of modularity
Jeff Clune, Jean-Baptiste Mouret, Hod Lipson · Clune J, Mouret J-B, Lipson H. 2013 The evolutionary origins of modularity. Proceedings of the Royal Society B. 280: 20122863 · Neuroscience & neural computation
A central biological question is how natural organisms are so evolvable (capable of quickly adapting to new environments).
- 2012-04arXiv 1204.3463Effects of Social Influence on the Wisdom of Crowds
Pavlin Mavrodiev, Claudio J. Tessone, Frank Schweitzer · Society, software & economics
Wisdom of crowds refers to the phenomenon that the aggregate prediction or forecast of a group of individuals can be surprisingly more accurate than most individuals in the group, and sometimes - than any of the individuals comprising it.
- 2011-11arXiv 1111.0352Revisiting k-means: New Algorithms via Bayesian Nonparametrics
Brian Kulis, Michael I. Jordan · Machine learning
Bayesian models offer great flexibility for clustering applications---Bayesian nonparametrics can be used for modeling infinite mixtures, and hierarchical Bayesian models can be utilized for sharing clusters across multiple data sets.
- 2011-03arXiv 1103.4601Doubly Robust Policy Evaluation and Learning
Miroslav Dudik, John Langford, Lihong Li · Machine learning
We study decision making in environments where the reward is only partially observed, but can be modeled as a function of an action and an observed context. This setting, known as contextual bandits, encompasses a wide variety of applications including health-care policy and Internet advertising.
- 2010-08arXiv 1008.4532Switching between Hidden Markov Models using Fixed Share
Wouter M. Koolen, Tim van Erven · Machine learning
In prediction with expert advice the goal is to design online prediction algorithms that achieve small regret (additional loss on the whole data) compared to a reference scheme.
- 2010-03arXiv 1003.5956Unbiased Offline Evaluation of Contextual-bandit-based News Article Recommendation Algorithms
Lihong Li, Wei Chu, John Langford et al. · Machine learning
Contextual bandit algorithms have become popular for online recommendation systems such as Digg, Yahoo! \emph{Offline} evaluation of the effectiveness of new algorithms in these applications is critical for protecting online user experiences but very challenging due to their "partial-label" nature.
- 2010-02arXiv 1003.0146A Contextual-Bandit Approach to Personalized News Article Recommendation
Lihong Li, Wei Chu, John Langford et al. · Presented at the Nineteenth International Conference on World Wide Web (WWW 2010), Raleigh, NC, USA, 2010 · Machine learning
Personalized web services strive to adapt their services (advertisements, news articles, etc) to individual users by making use of both content and user information.
- 2010-02arXiv 1002.3307Graph Zeta Function in the Bethe Free Energy and Loopy Belief Propagation
Yusuke Watanabe, Kenji Fukumizu · Advances in Neural Information Processing Systems 22, pages 2017-2025 · AI & agents
We propose a new approach to the analysis of Loopy Belief Propagation (LBP) by establishing a formula that connects the Hessian of the Bethe free energy with the edge zeta function.
- 2008-07arXiv 0807.1005Catching Up Faster by Switching Sooner: A Prequential Solution to the AIC-BIC Dilemma
Tim van Erven, Peter Grunwald, Steven de Rooij · Statistics & theory
Bayesian model averaging, model selection and its approximations such as BIC are generally statistically consistent, but sometimes achieve slower rates og convergence than other methods such as AIC and leave-one-out cross-validation.
- 2008-05arXiv 0805.3415On Upper-Confidence Bound Policies for Non-Stationary Bandit Problems
Aurélien Garivier, Eric Moulines · Statistics & theory
Multi-armed bandit problems are considered as a paradigm of the trade-off between exploring the environment to find profitable actions and exploiting what is already known.
- 2007-12arXiv 0712.3329Universal Intelligence: A Definition of Machine Intelligence
Shane Legg, Marcus Hutter · Minds & Machines, 17:4 (2007) pages 391-444 · AI & agents
A fundamental problem in artificial intelligence is that nobody really knows what intelligence is. The problem is especially acute when we need to consider artificial systems which are significantly different to humans.
Cited inStudy: Superintelligence
Built from every arXiv paper cited in our papers, posts, topic hubs, reports and research notes, with titles, authors, dates and abstracts from the arXiv API (updated 2026-11-12). Summaries are the opening sentences of each paper's own abstract, not our assessment; a citation means we used or checked the work, not that we endorse it. Fields follow each paper's primary arXiv category. Papers cited only outside arXiv (journals, proceedings) are not listed yet. Entries are generated from our citations, so a mistyped ID in a note would list the wrong paper; we remove those as we find them. Report a wrong entry.
