Search Results for author:
Found 12 papers, 4 papers with code
A Short Survey of Systematic Generalization
Recent improvements from different aspects are discussed.
On a Built-in Conflict between Deep Learning and Systematic Generalization
In this paper, we hypothesize that internal function sharing is one of the reasons to weaken o. o. d.
Efficiently Disentangle Causal Representations
This paper proposes an efficient approach to learning disentangled representations with causal mechanisms based on the difference of conditional probabilities in original and new distributions.
Concepts, Properties and an Approach for Compositional Generalization
Compositional generalization is the capacity to recognize and imagine a large amount of novel combinations from known components.
Gradient Descent Resists Compositionality
In this paper, we argue that gradient descent is one of the reasons that make compositionality learning hard during neural network optimization.
Necessary and Sufficient Conditions for Compositional Representations
Humans naturally use compositional representations for flexible recognition and expression, but current machine learning lacks such ability.
Grounded Compositional Generalization with Environment Interactions
Second, we apply entropy regularization to learn corresponding input components for each output component.
Transferability of Compositionality
To our best knowledge, this is the first work to focus on the transferability of compositionality, and it is orthogonal to existing efforts of learning compositional representations in training distribution.
Compositional Language Continual Learning
It also shows significant improvement in machine translation task.
Multi-AI competing and winning against humans in iterated Rock-Paper-Scissors game
We model and predict human competition behavior by combining many Markov Models with different fixed memory lengths (abbreviated as "multi-AI"), and develop an architecture of multi-AI with changeable parameters to adapt to different competition strategies.
Compositional Generalization for Primitive Substitutions
Compositional generalization is a basic mechanism in human language learning, but current neural networks lack such ability.
Zero-Shot Transfer VQA Dataset
Therefore, toaccelerate this research, we propose a newzero-shot transfer VQA(ZST-VQA)dataset by reorganizing the existing VQA v1. 0 dataset in the way that duringtraining, some words appear only in one module (i. e. questions) but not in theother (i. e. answers).
