Papers Systematic Generalization
“Systematic Generalization” 태그가 달린 논문 126편 · 필터 해제
Learning Algebraic Representation for Abstract Spatial-Temporal Reasoning
Is intelligence realized by connectionist or classicist? While connectionist approaches have achieved superhuman performance, there has been growing evidence that such task-specific superiority is particularly fragile in…
Abstract AlgebraSystematic GeneralizationInductive Biases for Deep Learning of Higher-Level Cognition
A fascinating hypothesis is that human and animal intelligence could be explained by a few principles (rather than an encyclopedic list of heuristics). If that hypothesis was correct, we could more easily both understand…
Deep LearningSystematic GeneralizationLearning from Task Descriptions
Typically, machine learning systems solve new tasks by training on thousands of examples. In contrast, humans can solve new tasks by reading some instructions, with perhaps an example or two. To take a step toward closin…
Systematic GeneralizationLearning to Execute Programs with Instruction Pointer Attention Graph Neural Networks
Graph neural networks (GNNs) have emerged as a powerful tool for learning software engineering tasks including code completion, bug finding, and program repair. They benefit from leveraging program structure like control…
Code CompletionLearning to ExecuteProgram RepairProgram Synthesis+1Prioritized Level Replay
Environments with procedurally generated content serve as important benchmarks for testing systematic generalization in deep reinforcement learning. In this setting, each level is an algorithmically created environment i…
Deep Reinforcement LearningSystematic GeneralizationCURI: A Benchmark for Productive Concept Learning Under Uncertainty
Humans can learn and reason under substantial uncertainty in a space of infinitely many concepts, including structured relational concepts ("a scene with objects that have the same color") and ad-hoc categories defined t…
Meta-LearningSystematic GeneralizationAre Neural Nets Modular? Inspecting Functional Modularity Through Differentiable Weight Masks
Neural networks (NNs) whose subnetworks implement reusable functions are expected to offer numerous advantages, including compositionality through efficient recombination of functional building blocks, interpretability, …
Systematic GeneralizationMeasuring Systematic Generalization in Neural Proof Generation with Transformers
We are interested in understanding how well Transformer language models (TLMs) can perform reasoning tasks when trained on knowledge encoded in the form of natural language. We investigate their systematic generalization…
Automated Theorem ProvingLogical ReasoningSystematic GeneralizationSystematic Generalization on gSCAN with Language Conditioned Embedding
Systematic Generalization refers to a learning algorithm's ability to extrapolate learned behavior to unseen situations that are distinct but semantically similar to its training data. As shown in recent work, state-of-t…
Systematic GeneralizationCompositional Networks Enable Systematic Generalization for Grounded Language Understanding
Humans are remarkably flexible when understanding new sentences that include combinations of concepts they have never encountered before. Recent work has shown that while deep networks can mimic some human language abili…
Systematic GeneralizationCompositional Generalization by Factorizing Alignment and Translation
Standard methods in deep learning for natural language processing fail to capture the compositional structure of human language that allows for systematic generalization outside of the training distribution. However, hum…
Machine TranslationSystematic GeneralizationTranslationCompositionality and Capacity in Emergent Languages
Recent works have discussed the extent to which emergent languages can exhibit properties of natural languages particularly learning compositionality. In this paper, we investigate the learning biases that affect the eff…
Open-Ended Question AnsweringSystematic GeneralizationLatent Compositional Representations Improve Systematic Generalization in Grounded Question Answering
Answering questions that involve multi-step reasoning requires decomposing them and using the answers of intermediate steps to reach the final answer. However, state-of-the-art models in grounded question answering often…
Inductive BiasQuestion AnsweringSystematic GeneralizationThe NetHack Learning Environment
Progress in Reinforcement Learning (RL) algorithms goes hand-in-hand with the development of challenging environments that test the limits of current methods. While existing RL environments are either sufficiently comple…
NetHackNetHack ScoreReinforcement Learning (RL)Systematic GeneralizationA Generalised Linear Model Framework for $β$-Variational Autoencoders based on Exponential Dispersion Families
Although variational autoencoders (VAE) are successfully used to obtain meaningful low-dimensional representations for high-dimensional data, the characterization of critical points of the loss function for general obser…
Systematic GeneralizationNeural Natural Language Inference Models Partially Embed Theories of Lexical Entailment and Negation
We address whether neural models for Natural Language Inference (NLI) can learn the compositional interactions between lexical entailment and negation, using four methods: the behavioral evaluation methods of (1) challen…
Lexical EntailmentNatural Language InferenceNegationSystematic GeneralizationRevisit Systematic Generalization via Meaningful Learning
Humans can systematically generalize to novel compositions of existing concepts. Recent studies argue that neural networks appear inherently ineffective in such cognitive capacity, leading to a pessimistic view and a lac…
Data AugmentationMachine TranslationNovel ConceptsSemantic Parsing+1A Benchmark for Systematic Generalization in Grounded Language Understanding
Humans easily interpret expressions that describe unfamiliar situations composed from familiar parts ("greet the pink brontosaurus by the ferris wheel"). Modern neural networks, by contrast, struggle to interpret novel c…
Systematic GeneralizationCLOSURE: Assessing Systematic Generalization of CLEVR Models
The CLEVR dataset of natural-looking questions about 3D-rendered scenes has recently received much attention from the research community. A number of models have been proposed for this task, many of which achieved very h…
Few-Shot LearningSystematic GeneralizationTransfer LearningCapacity, Bandwidth, and Compositionality in Emergent Language Learning
Many recent works have discussed the propensity, or lack thereof, for emergent languages to exhibit properties of natural languages. A favorite in the literature is learning compositionality. We note that most of those w…
Open-Ended Question AnsweringSystematic Generalization