Machine Learning
Communicative Learning: A Unified Learning Formalism
Download Abstract: In this article, we propose a communicative learning (CL) formalism that unifies existing machine learning paradigms, such as passive learning, active learning, algorithmic teaching, and so forth, and facilitates the development of new learning methods. Arising from human cooperative communication, this formalism poses learning as a communicative process and combines pedagogy with the …
Communicative Learning: A Unified Learning Formalism Read More »
SQA3D: Situated Question Answering in 3D Scenes
Download Abstract: We propose a new task to benchmark scene understanding of embodied agents: Situated Question Answering in 3D Scenes (SQA3D). Given a scene context (e.g., 3D scan), SQA3D requires the tested agent to first understand its situation (position, orientation, etc.) in the 3D scene as described by text, then reason about its surrounding environment …
A Minimalist Dataset for Systematic Generalization of Perception, Syntax, and Semantics
Download Abstract: Inspired by humans’ exceptional ability to master arithmetic and generalize to new problems, we present a new dataset, HINT, to examine machines’ capability of learning generalizable concepts at three levels: perception, syntax, and semantics. In HINT, machines are tasked with learning how concepts are perceived from raw signals such as images (i.e., perception), …
A Minimalist Dataset for Systematic Generalization of Perception, Syntax, and Semantics Read More »