Search Results for author:
Found 29 papers, 11 papers with code
Understanding the Limits of Vision Language Models Through the Lens of the Binding Problem
Recent work has documented striking heterogeneity in the performance of state-of-the-art vision language models (VLMs), including both multimodal language models and text-to-image models.
Slot Abstractors: Toward Scalable Abstract Visual Reasoning
Abstract visual reasoning is a characteristically human ability, allowing the identification of relational patterns that are abstracted away from object features, and the systematic generalization of those patterns to unseen problems.
A Relational Inductive Bias for Dimensional Abstraction in Neural Networks
The human cognitive system exhibits remarkable flexibility and generalization capabilities, partly due to its ability to form low-dimensional, compositional representations of the environment.
Human-Like Geometric Abstraction in Large Pre-trained Neural Networks
Humans possess a remarkable capacity to recognize and manipulate abstract structure, which is especially apparent in the domain of geometry.
Relational Constraints On Neural Networks Reproduce Human Biases towards Abstract Geometric Regularity
Uniquely among primates, humans possess a remarkable capacity to recognize and manipulate abstract structure in the service of task goals across a broad range of behaviors.
The Relational Bottleneck as an Inductive Bias for Efficient Abstraction
A central challenge for cognitive science is to explain how abstract concepts are acquired from limited experience.
A Quantitative Approach to Predicting Representational Learning and Performance in Neural Networks
A key property of neural networks (both biological and artificial) is how they learn to represent and manipulate input information in order to solve a task.
Systematic Visual Reasoning through Object-Centric Relational Abstraction
Human visual reasoning is characterized by an ability to identify abstract patterns from only a small number of examples, and to systematically generalize those patterns to novel inputs.
Determinantal Point Process Attention Over Grid Cell Code Supports Out of Distribution Generalization
Deep neural networks have made tremendous gains in emulating human-like intelligence, and have been used increasingly as ways of understanding how the brain may solve the complex computational problems on which this relies.
Learning to reason over visual objects
These results suggest that an inductive bias for object-centric processing may be a key component of abstract visual reasoning, obviating the need for problem-specific inductive biases.
Using Natural Language and Program Abstractions to Instill Human Inductive Biases in Machines
Co-training on these representations result in more human-like behavior in downstream meta-reinforcement learning agents than less abstract controls (synthetic language descriptions, program induction without learned primitives), suggesting that the abstraction supported by these representations is key.
Modularity benefits reinforcement learning agents with competing homeostatic drives
The problem of balancing conflicting needs is fundamental to intelligence.
Disentangling Abstraction from Statistical Pattern Matching in Human and Machine Learning
However, because neural networks are hard to interpret, it can be difficult to tell whether agents have learned the underlying abstraction, or alternatively statistical patterns that are characteristic of that abstraction.
A Self-Supervised Framework for Function Learning and Extrapolation
Understanding how agents learn to generalize -- and, in particular, to extrapolate -- in high-dimensional, naturalistic environments remains a challenge for both machine learning and the study of biological agents.
People construct simplified mental representations to plan
We propose a computational account of this simplification process and, in a series of pre-registered behavioral experiments, show that it is subject to online cognitive control and that people optimally balance the complexity of a task representation and its utility for planning and acting.
Human Inference in Changing Environments With Temporal Structure
We show that humans adapt their inference process to fine aspects of the temporal structure in the statistics of stimuli.
Emergent Symbols through Binding in External Memory
A key aspect of human intelligence is the ability to infer abstract rules directly from high-dimensional sensory data, and to do so given only a limited amount of training experience.
A Memory-Augmented Neural Network Model of Abstract Rule Learning
Further, we introduce the Emergent Symbol Binding Network (ESBN), a recurrent neural network model that learns to use an external memory as a binding mechanism.
A Mitigation Score for COVID-19
This note describes a simple score to indicate the effectiveness of mitigation against infections of COVID-19 as observed by new case counts.
Meta-Learning of Structured Task Distributions in Humans and Machines
We then introduce a novel approach to constructing a "null task distribution" with the same statistical complexity as this structured task distribution but without the explicit rule-based structure used to generate the structured task.
Navigating the Trade-Off between Multi-Task Learning and Learning to Multitask in Deep Neural Networks
The terms multi-task learning and multitasking are easily confused.
Learning Representations that Support Extrapolation
Extrapolation -- the ability to make inferences that go beyond the scope of one's experiences -- is a hallmark of human intelligence.
The Efficiency of Human Cognition Reflects Planned Information Processing
Thus, people should plan their actions, but they should also be smart about how they deploy resources used for planning their actions.
Context Matters: Recovering Human Semantic Structure from Machine Learning Analysis of Large-Scale Text Corpora
Applying machine learning algorithms to large-scale, text-based corpora (embeddings) presents a unique opportunity to investigate at scale how human semantic knowledge is organized and how people use it to judge fundamental relationships, such as similarity between concepts.
A graph-theoretic approach to multitasking
A key feature of neural network architectures is their ability to support the simultaneous interaction among large numbers of units in the learning and processing of representations.
Matrix-normal models for fMRI analysis
We show how the matrix-variate normal (MN) formalism can unify some of these methods into a single framework.
A Theory of Decision Making Under Dynamic Context
We also show how the model generalizes re- cent work on the control of attention in the Flanker task (Yu et al., 2009).
Learning to Use Working Memory in Partially Observable Environments through Dopaminergic Reinforcement
Working memory is a central topic of cognitive neuroscience because it is critical for solving real world problems in which information from multiple temporally distant sources must be combined to generate appropriate behavior.
Sequential effects: Superstition or rational behavior?
In a variety of behavioral tasks, subjects exhibit an automatic and apparently sub-optimal sequential effect: they respond more rapidly and accurately to a stimulus if it reinforces a local pattern in stimulus history, such as a string of repetitions or alternations, compared to when it violates such a pattern.
