98 citations · 352 across the 15 of their papers we have counts for
18 papers
Successor-Predecessor Intrinsic Exploration
Changmin Yu, Neil Burgess, Maneesh Sahani +1
Exploration is essential in reinforcement learning, particularly in environments where external rewards are sparse. Here we focus on exploration with intrinsic rewards, where the a…
The molecular memory code and synaptic plasticity: a synthesis
Samuel J. Gershman
The most widely accepted view of memory in the brain holds that synapses are the storage sites of memory, and that memories are formed through associative modification of synapses.…
Representation learning with reward prediction errors
William H. Alexander, Samuel J. Gershman
The Reward Prediction Error hypothesis proposes that phasic activity in the midbrain dopaminergic system reflects prediction errors needed for learning in reinforcement learning. B…
Human-Level Reinforcement Learning through Theory-Based Modeling, Exploration, and Planning
Pedro A. Tsividis, Joao Loula, Jake Burga +5
Reinforcement learning (RL) studies how an agent comes to achieve reward in an environment through interactions over time. Recent advances in machine RL have surpassed human expert…
Hybrid Memoised Wake-Sleep: Approximate Inference at the Discrete-Continuous Interface
Tuan Anh Le, Katherine M. Collins, Luke Hewitt +4
Modeling complex phenomena typically involves the use of both discrete and continuous variables. Such a setting applies across a wide range of problems, from identifying trends in…
Language-Mediated, Object-Centric Representation Learning
Ruocheng Wang, Jiayuan Mao, Samuel J. Gershman +1
We present Language-mediated, Object-centric Representation Learning (LORL), a paradigm for learning disentangled, object-centric scene representations from vision and language. LO…
Analyzing machine-learned representations: A natural language case study
Ishita Dasgupta, Demi Guo, Samuel J. Gershman +1
As modern deep networks become more complex, and get closer to human-like capabilities in certain domains, the question arises of how the representations and decision rules they le…
What does the free energy principle tell us about the brain?
Samuel J. Gershman
The free energy principle has been proposed as a unifying account of brain function. It is closely related, and in some cases subsumes, earlier unifying ideas such as Bayesian infe…
Human-in-the-Loop Interpretability Prior
Isaac Lage, Andrew Slavin Ross, Been Kim +2
We often desire our models to be interpretable as well as accurate. Prior work on optimizing models for interpretability has relied on easy-to-quantify proxies for interpretability…
How do Humans Understand Explanations from Machine Learning Systems? An Evaluation of the Human-Interpretability of Explanation
Menaka Narayanan, Emily Chen, Jeffrey He +3
Recent years have seen a boom in interest in machine learning systems that can provide a human-understandable rationale for their predictions or decisions. However, exactly what ki…
Estimating scale-invariant future in continuous time
Zoran Tiganj, Samuel J. Gershman, Per B. Sederberg +1
Natural learners must compute an estimate of future outcomes that follow from a stimulus in continuous time. Widely used reinforcement learning algorithms discretize continuous tim…
Evaluating Compositionality in Sentence Embeddings
Ishita Dasgupta, Demi Guo, Andreas Stuhlmüller +2
An important challenge for human-like AI is compositional semantics. Recent research has attempted to address this by using deep neural networks to learn vector space embeddings of…
Accountability of AI Under the Law: The Role of Explanation
Finale Doshi-Velez, Mason Kortz, Ryan Budish +9
The ubiquity of systems using artificial intelligence or "AI" has brought increasing attention to how those systems should be regulated. The choice of how to regulate AI systems wi…
Deep Successor Reinforcement Learning
Tejas D. Kulkarni, Ardavan Saeedi, Simanta Gautam +1
Learning robust value functions given raw observations and rewards is now possible with model-free and model-based deep reinforcement learning algorithms. There is a third alternat…
Nonparametric Spherical Topic Modeling with Word Embeddings
Kayhan Batmanghelich, Ardavan Saeedi, Karthik Narasimhan +1
Traditional topic models do not account for semantic regularities in language. Recent distributional representations of words exhibit semantic consistency over directional metrics…
Variational Particle Approximations
Ardavan Saeedi, Tejas D Kulkarni, Vikash Mansinghka +1
Approximate inference in high-dimensional, discrete probabilistic models is a central problem in computational statistics and machine learning. This paper describes discrete partic…
Nonparametric variational inference
Samuel Gershman, Matt Hoffman, David Blei
Variational methods are widely used for approximate posterior inference. However, their use is typically limited to families of distributions that enjoy particular conjugacy proper…
Distance Dependent Infinite Latent Feature Models
Samuel J. Gershman, Peter I. Frazier, David M. Blei
Latent feature models are widely used to decompose data into a small number of components. Bayesian nonparametric variants of these models, which use the Indian buffet process (IBP…