Human-like generalization in a machine through predicate learning
Humans readily generalize, applying prior knowledge to novel situations and stimuli. Advances in machine learning and artificial intelligence have begun to approximate and even surpass human performance, but machine systems reliably struggle to generalize information to untrained situations. We describe a neural network model that is trained to play one video game (Breakout) and demonstrates one-shot generalization to a new game (Pong). The model generalizes by learning representations that are functionally and formally symbolic from training data, without feedback, and without requiring that structured representations be specified a priori. The model uses unsupervised comparison to discover which characteristics of the input are invariant, and to learn relational predicates; it then applies these predicates to arguments in a symbolic fashion, using oscillatory regularities in network firing to dynamically bind predicates to arguments. We argue that models of human cognition must account for far-reaching and flexible generalization, and that in order to do so, models must be able to discover symbolic representations from unstructured data, a process we call predicate learning. Only then can models begin to adequately explain where human-like representations come from, why human cognition is the way it is, and why it continues to differ from machine intelligence in crucial ways.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Learning Semantic Structure through First-Order-Logic Translation
In this paper, we study whether transformer-based language models can extract predicate argument structure from simple sentences. We firstly show that language models sometimes confuse which predicates apply to which obj…
Question AnsweringTranslationSocial AI and The Equation of Wittgenstein's Language User With Calvino's Literature Machine
Is it sensical to ascribe psychological predicates to AI systems like chatbots based on large language models (LLMs)? People have intuitively started ascribing emotions or consciousness to social AI ('affective artificia…
Novel Human-Object Interaction Detection via Adversarial Domain Generalization
We study in this paper the problem of novel human-object interaction (HOI) detection, aiming at improving the generalization ability of the model to unseen scenarios. The challenge mainly stems from the large composition…
Domain GeneralizationHuman-Object Interaction DetectionObjectTripletHEIDL: Learning Linguistic Expressions with Deep Learning and Human-in-the-Loop
While the role of humans is increasingly recognized in machine learning community, representation of and interaction with models in current human-in-the-loop machine learning (HITL-ML) approaches are too low-level and fa…
BIG-bench Machine LearningEmbodied Active Learning of Relational State Abstractions for Bilevel Planning
State abstraction is an effective technique for planning in robotics environments with continuous states and actions, long task horizons, and sparse feedback. In object-oriented environments, predicates are a particularl…
Active LearningInformativeness