-
Emergent Symbols through Binding in External Memory
A key aspect of human intelligence is the ability to infer abstract rule...
12/29/2020 ∙ by Taylor W. Webb, et al. ∙
2
∙
share
read it
-
A Memory-Augmented Neural Network Model of Abstract Rule Learning
Human intelligence is characterized by a remarkable ability to infer abs...
12/13/2020 ∙ by Ishan Sinha, et al. ∙
21
∙
share
read it
-
Meta-Learning of Compositional Task Distributions in Humans and Machines
Modern machine learning systems struggle with sample efficiency and are ...
10/05/2020 ∙ by Sreejan Kumar, et al. ∙
0
∙
share
read it
-
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. Mult...
07/20/2020 ∙ by Sachin Ravi, et al. ∙
0
∙
share
read it
-
Learning Representations that Support Extrapolation
Extrapolation – the ability to make inferences that go beyond the scope ...
07/09/2020 ∙ by Taylor W. Webb, et al. ∙
9
∙
share
read it
-
The Efficiency of Human Cognition Reflects Planned Information Processing
Planning is useful. It lets people take actions that have desirable long...
02/13/2020 ∙ by Mark K Ho, et al. ∙
7
∙
share
read it
-
Context Matters: Recovering Human Semantic Structure from Machine Learning Analysis of Large-Scale Text Corpora
Understanding how human semantic knowledge is organized and how people u...
10/15/2019 ∙ by Marius Cătălin Iordan, et al. ∙
0
∙
share
read it
-
Multitasking Capacity: Hardness Results and Improved Constructions
We consider the problem of determining the maximal α∈ (0,1] such that ev...
09/08/2018 ∙ by Noga Alon, et al. ∙
0
∙
share
read it
-
Matrix-normal models for fMRI analysis
Multivariate analysis of fMRI data has benefited substantially from adva...
11/08/2017 ∙ by Michael Shvartsman, et al. ∙
0
∙
share
read it
