Human-like systematic generalization through a meta-learning neural network
The power of human language and thought arises from systematic compositionality—the
algebraic ability to understand and produce novel combinations from known components …
algebraic ability to understand and produce novel combinations from known components …
How to reuse and compose knowledge for a lifetime of tasks: A survey on continual learning and functional composition
A major goal of artificial intelligence (AI) is to create an agent capable of acquiring a general
understanding of the world. Such an agent would require the ability to continually …
understanding of the world. Such an agent would require the ability to continually …
Induced natural language rationales and interleaved markup tokens enable extrapolation in large language models
The ability to extrapolate, ie, to make predictions on sequences that are longer than those
presented as training examples, is a challenging problem for current deep learning models …
presented as training examples, is a challenging problem for current deep learning models …
Revisiting iterative back-translation from the perspective of compositional generalization
Human intelligence exhibits compositional generalization (ie, the capacity to understand
and produce unseen combinations of seen components), but current neural seq2seq …
and produce unseen combinations of seen components), but current neural seq2seq …
Neural-symbolic recursive machine for systematic generalization
Despite the tremendous success, existing machine learning models still fall short of human-
like systematic generalization--learning compositional rules from limited data and applying …
like systematic generalization--learning compositional rules from limited data and applying …
Beam tree recursive cells
JR Chowdhury, C Caragea - International Conference on …, 2023 - proceedings.mlr.press
Abstract We propose Beam Tree Recursive Cell (BT-Cell)-a backpropagation-friendly
framework to extend Recursive Neural Networks (RvNNs) with beam search for latent …
framework to extend Recursive Neural Networks (RvNNs) with beam search for latent …
Modeling hierarchical structures with continuous recursive neural networks
JR Chowdhury, C Caragea - International Conference on …, 2021 - proceedings.mlr.press
Abstract Recursive Neural Networks (RvNNs), which compose sequences according to their
underlying hierarchical syntactic structure, have performed well in several natural language …
underlying hierarchical syntactic structure, have performed well in several natural language …
Machine Learning and Data Analysis Using Posets: A Survey
AM Mwafise - arXiv preprint arXiv:2404.03082, 2024 - arxiv.org
Posets are discrete mathematical structures which are ubiquitous in a broad range of data
analysis and machine learning applications. Research connecting posets to the data …
analysis and machine learning applications. Research connecting posets to the data …
Layer-Wise Representation Fusion for Compositional Generalization
Y Zheng, L Lin, S Li, Y Yuan, Z Lai, S Liu, B Fu… - Proceedings of the …, 2024 - ojs.aaai.org
Existing neural models are demonstrated to struggle with compositional generalization (CG),
ie, the ability to systematically generalize to unseen compositions of seen components. A …
ie, the ability to systematically generalize to unseen compositions of seen components. A …
MER: Modular Element Randomization for robust generalizable policy in deep reinforcement learning
Y Li, J Ren, T Zhang, Y Fang, F Chen - Knowledge-Based Systems, 2023 - Elsevier
Improving the generalization ability of reinforcement learning (RL) agents is an open and
challenging problem and has gradually received attention in recent years. Previous work …
challenging problem and has gradually received attention in recent years. Previous work …