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.
- 2017-12arXiv 1712.04577Learning From Noisy Singly-labeled Data
Ashish Khetan, Zachary C. Lipton, Anima Anandkumar · Machine learning
Supervised learning depends on annotated examples, which are taken to be the \emph{ground truth}. But these labels often come from noisy crowdsourcing platforms, like Amazon Mechanical Turk.
- 2017-12arXiv 1712.03847On Quadratic Penalties in Elastic Weight Consolidation
Ferenc Huszár · Machine learning
Elastic weight consolidation (EWC, Kirkpatrick et al, 2017) is a novel algorithm designed to safeguard against catastrophic forgetting in neural networks.
- 2017-11arXiv 1711.11157A Semantic Loss Function for Deep Learning with Symbolic Knowledge
Jingyi Xu, Zilu Zhang, Tal Friedman et al. · AI & agents
This paper develops a novel methodology for using symbolic knowledge in deep learning. From first principles, we derive a semantic loss function that bridges between neural output vectors and logical constraints.
- 2017-11arXiv 1711.10160Snorkel: Rapid Training Data Creation with Weak Supervision
Alexander Ratner, Stephen H. Bach, Henry Ehrenberg et al. · Proceedings of the VLDB Endowment, 11(3), 269-282, 2017 · Machine learning
Labeling training data is increasingly the largest bottleneck in deploying machine learning systems. We present Snorkel, a first-of-its-kind system that enables users to train state-of-the-art models without hand labeling any training data.
- 2017-11arXiv 1711.09601Memory Aware Synapses: Learning what (not) to forget
Rahaf Aljundi, Francesca Babiloni, Mohamed Elhoseiny et al. · Vision
Humans can learn in a continuous manner. Old rarely utilized knowledge can be overwritten by new incoming information while important, frequently used knowledge is prevented from being erased.
- 2017-11arXiv 1711.09846Population Based Training of Neural Networks
Max Jaderberg, Valentin Dalibard, Simon Osindero et al. · Machine learning
Neural networks dominate the modern machine learning landscape, but their training and success still suffer from sensitivity to empirical choices of hyperparameters such as model architecture, loss function, and optimisation algorithm.
- 2017-11arXiv 1711.05769PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning
Arun Mallya, Svetlana Lazebnik · Vision
This paper presents a method for adding multiple tasks to a single deep neural network while avoiding catastrophic forgetting. Inspired by network pruning techniques, we exploit redundancies in large deep networks to free up parameters that can then be employed to learn new tasks.
- 2017-10arXiv 1710.10628Variational Continual Learning
Cuong V. Nguyen, Yingzhen Li, Thang D. Bui et al. · Machine learning
This paper develops variational continual learning (VCL), a simple but general framework for continual learning that fuses online variational inference (VI) and recent advances in Monte Carlo VI for neural networks.
- 2017-08arXiv 1708.01547Lifelong Learning with Dynamically Expandable Networks
Jaehong Yoon, Eunho Yang, Jeongtae Lee et al. · Machine learning
We propose a novel deep network architecture for lifelong learning which we refer to as Dynamically Expandable Network (DEN), that can dynamically decide its network capacity as it trains on a sequence of tasks, to learn a compact overlapping knowledge sharing structure among tasks.
- 2017-07arXiv 1707.06347Proximal Policy Optimization Algorithms
John Schulman, Filip Wolski, Prafulla Dhariwal et al. · Machine learning
We propose a new family of policy gradient methods for reinforcement learning, which alternate between sampling data through interaction with the environment, and optimizing a "surrogate" objective function using stochastic gradient ascent.
- 2017-07arXiv 1707.04227Automatic Speech Recognition with Very Large Conversational Finnish and Estonian Vocabularies
Seppo Enarvi, Peter Smit, Sami Virpioja et al. · IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 25, no. 11, pp. 2085-2097, November 2017 · Language models & NLP
Today, the vocabulary size for language models in large vocabulary speech recognition is typically several hundreds of thousands of words. While this is already sufficient in some applications, the out-of-vocabulary words are still limiting the usability in others.
- 2017-07arXiv 1707.00355Evaluating Ising Processing Units with Integer Programming
Carleton Coffrin, Harsha Nagarajan, Russell Bent · Statistics & theory
The recent emergence of novel computational devices, such as adiabatic quantum computers, CMOS annealers, and optical parametric oscillators, present new opportunities for hybrid-optimization algorithms that are hardware accelerated by these devices.
- 2017-07arXiv 1707.00183Teacher-Student Curriculum Learning
Tambet Matiisen, Avital Oliver, Taco Cohen et al. · Machine learning
We propose Teacher-Student Curriculum Learning (TSCL), a framework for automatic curriculum learning, where the Student tries to learn a complex task and the Teacher automatically chooses subtasks from a given set for the Student to train on.
- 2017-06arXiv 1706.08840Gradient Episodic Memory for Continual Learning
David Lopez-Paz, Marc'Aurelio Ranzato · Machine learning
One major obstacle towards AI is the poor ability of models to solve new problems quicker, and without forgetting previously acquired knowledge.
- 2017-05arXiv 1705.10257Boltzmann Exploration Done Right
Nicolò Cesa-Bianchi, Claudio Gentile, Gábor Lugosi et al. · Machine learning
Boltzmann exploration is a classic strategy for sequential decision-making under uncertainty, and is one of the most standard tools in Reinforcement Learning (RL).
- 2017-05arXiv 1705.08690Continual Learning with Deep Generative Replay
Hanul Shin, Jung Kwon Lee, Jaehong Kim et al. · AI & agents
Attempts to train a comprehensive artificial intelligence capable of solving multiple tasks have been impeded by a chronic problem called catastrophic forgetting.
- 2017-05arXiv 1705.08500Selective Classification for Deep Neural Networks
Yonatan Geifman, Ran El-Yaniv · Machine learning
Selective classification techniques (also known as reject option) have not yet been considered in the context of deep neural networks (DNNs). These techniques can potentially significantly improve DNNs prediction performance by trading-off coverage.
- 2017-04arXiv 1704.03003Automated Curriculum Learning for Neural Networks
Alex Graves, Marc G. Bellemare, Jacob Menick et al. · Neuroscience & neural computation
We introduce a method for automatically selecting the path, or syllabus, that a neural network follows through a curriculum so as to maximise learning efficiency.
- 2017-04arXiv 1704.02030Using stacking to average Bayesian predictive distributions
Yuling Yao, Aki Vehtari, Daniel Simpson et al. · Statistics & theory
The widely recommended procedure of Bayesian model averaging is flawed in the M-open setting in which the true data-generating process is not one of the candidate models being fit.
- 2017-03arXiv 1703.08475Overcoming Catastrophic Forgetting by Incremental Moment Matching
Sang-Woo Lee, Jin-Hwa Kim, Jaehyun Jun et al. · Machine learning
Catastrophic forgetting is a problem of neural networks that loses the information of the first task after training the second task. incremental moment matching (IMM), to resolve this problem.
- 2017-03arXiv 1703.04987Equilibrated flux a posteriori error estimates in -norms for high-order discretizations of parabolic problems
Alexandre Ern, Iain Smears, Martin Vohralik · IMA Journal of Numerical Analysis, 2018 · Statistics & theory
We consider the a posteriori error analysis of fully discrete approximations of parabolic problems based on conforming -finite element methods in space and an arbitrary order discontinuous Galerkin method in time.
- 2017-03arXiv 1703.05407Intrinsic Motivation and Automatic Curricula via Asymmetric Self-Play
Sainbayar Sukhbaatar, Zeming Lin, Ilya Kostrikov et al. · Machine learning
We describe a simple scheme that allows an agent to learn about its environment in an unsupervised manner. Our scheme pits two versions of the same agent, Alice and Bob, against one another.
- 2017-03arXiv 1703.04730Understanding Black-box Predictions via Influence Functions
Pang Wei Koh, Percy Liang · Machine learning
How can we explain the predictions of a black-box model?
- 2017-03arXiv 1703.04200Continual Learning Through Synaptic Intelligence
Friedemann Zenke, Ben Poole, Surya Ganguli · Machine learning
While deep learning has led to remarkable advances across diverse applications, it struggles in domains where the data distribution changes over the course of learning.
- 2017-03arXiv 1703.01780Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
Antti Tarvainen, Harri Valpola · Neuroscience & neural computation
The recently proposed Temporal Ensembling has achieved state-of-the-art results in several semi-supervised learning benchmarks. It maintains an exponential moving average of label predictions on each training example, and penalizes predictions that are inconsistent with this target.
- 2017-03arXiv 1703.01357A Computational Model of Systems Memory Consolidation and Reconsolidation
Peter Helfer, Thomas R. Shultz · Hippocampus, 30, (2020) 659-677 · Neuroscience & neural computation
In the mammalian brain, newly acquired memories depend on the hippocampus for maintenance and recall, but over time the neocortex takes over these functions, rendering memories hippocampus-independent.
- 2017-01arXiv 1701.08734PathNet: Evolution Channels Gradient Descent in Super Neural Networks
Chrisantha Fernando, Dylan Banarse, Charles Blundell et al. · Neuroscience & neural computation
For artificial general intelligence (AGI) it would be efficient if multiple users trained the same giant neural network, permitting parameter reuse, without catastrophic forgetting.
- 2017-01arXiv 1701.06538Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer
Noam Shazeer, Azalia Mirhoseini, Krzysztof Maziarz et al. · Machine learning
The capacity of a neural network to absorb information is limited by its number of parameters.
- 2016-12arXiv 1612.04844The More You Know: Using Knowledge Graphs for Image Classification
Kenneth Marino, Ruslan Salakhutdinov, Abhinav Gupta · Vision
One characteristic that sets humans apart from modern learning-based computer vision algorithms is the ability to acquire knowledge about the world and use that knowledge to reason about the visual world.
- 2016-12arXiv 1612.00796Overcoming catastrophic forgetting in neural networks
James Kirkpatrick, Razvan Pascanu, Neil Rabinowitz et al. · Machine learning
The ability to learn tasks in a sequential fashion is crucial to the development of artificial intelligence. Neural networks are not, in general, capable of this and it has been widely thought that catastrophic forgetting is an inevitable feature of connectionist models.
Cited inEWC protects what its Fisher sees: a literature synthesis on elastic weight consolidation, scale and coherenceEWC stiffness freezes stale facts, and no per-fact Fisher ledger can release itStudy: Decision signatures for conflict detectionStudy: Elastic weight consolidation deep diveStudy: Fortifying knowledge in continual learning - 2016-11arXiv 1611.06194Expert Gate: Lifelong Learning with a Network of Experts
Rahaf Aljundi, Punarjay Chakravarty, Tinne Tuytelaars · Vision
In this paper we introduce a model of lifelong learning, based on a Network of Experts. New tasks / experts are learned and added to the model sequentially, building on what was learned before.
- 2016-10arXiv 1610.06258Using Fast Weights to Attend to the Recent Past
Jimmy Ba, Geoffrey Hinton, Volodymyr Mnih et al. · Machine learning
Until recently, research on artificial neural networks was largely restricted to systems with only two types of variable: Neural activities that represent the current or recent input and weights that learn to capture regularities among inputs, outputs and payoffs.
- 2016-09arXiv 1609.09106HyperNetworks
David Ha, Andrew Dai, Quoc V. Le · Machine learning
This work explores hypernetworks: an approach of using a one network, also known as a hypernetwork, to generate the weights for another network.
- 2016-09arXiv 1609.03543Logical Induction
Scott Garrabrant, Tsvi Benson-Tilsen, Andrew Critch et al. · AI & agents
We present a computable algorithm that assigns probabilities to every logical statement in a given formal language, and refines those probabilities over time.
- 2016-06arXiv 1606.09282Learning without Forgetting
Zhizhong Li, Derek Hoiem · Vision
When building a unified vision system or gradually adding new capabilities to a system, the usual assumption is that training data for all tasks is always available.
- 2016-06arXiv 1606.04671Progressive Neural Networks
Andrei A. Rusu, Neil C. Rabinowitz, Guillaume Desjardins et al. · Machine learning
Learning to solve complex sequences of tasks--while both leveraging transfer and avoiding catastrophic forgetting--remains a key obstacle to achieving human-level intelligence.
- 2016-06arXiv 1606.01164Dense Associative Memory for Pattern Recognition
Dmitry Krotov, John J Hopfield · Advances in Neural Information Processing Systems 29 (2016), 1172-1180 · Neuroscience & neural computation
A model of associative memory is studied, which stores and reliably retrieves many more patterns than the number of neurons in the network. We propose a simple duality between this dense associative memory and neural networks commonly used in deep learning.
- 2016-05arXiv 1605.09522Kernel Mean Embedding of Distributions: A Review and Beyond
Krikamol Muandet, Kenji Fukumizu, Bharath Sriperumbudur et al. · Foundations and Trends in Machine Learning: Vol. 10: No. 1-2, pp 1-141 (2017) · Machine learning
A Hilbert space embedding of a distribution---in short, a kernel mean embedding---has recently emerged as a powerful tool for machine learning and inference.
- 2016-05arXiv 1605.03142Self-Modification of Policy and Utility Function in Rational Agents
Tom Everitt, Daniel Filan, Mayank Daswani et al. · AI & agents
Any agent that is part of the environment it interacts with and has versatile actuators (such as arms and fingers), will in principle have the ability to self-modify -- for example by changing its own source code.
- 2016-02arXiv 1602.04938"Why Should I Trust You?": Explaining the Predictions of Any Classifier
Marco Tulio Ribeiro, Sameer Singh, Carlos Guestrin · Machine learning
Despite widespread adoption, machine learning models remain mostly black boxes. Understanding the reasons behind predictions is, however, quite important in assessing trust, which is fundamental if one plans to take action based on a prediction, or when choosing whether to deploy a new model.
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.
