paper-with-me

홈 › Papers

Learning to Represent State with Perceptual Schemata

2021-06-13 · ICML Workshop URL 2021 7 · Wilka Torrico Carvalho, Murray Shanahan

The real world is large and complex. It is filled with many objects besides those defined by a task and objects can move with their own interesting dynamics. How should an agent learn to represent state to support efficient learning and generalization in such an environment? In this work, we present a novel memory architecture, Perceptual Schemata, for learning and zero-shot generalization in environments that have many, potentially moving objects. Perceptual Schemata represents state using a combination of schema modules that each learn to attend to and maintain stateful representations of different subspaces of a spatio-temporal tensor describing the agent’s observations. We present empirical results that Perceptual Schemata enables a state representation that can maintain multiple objects observed in sequence with independent dynamics while an LSTM cannot. We additionally show that Perceptual Schemata can generalize more gracefully to larger environments with more distractor objects, while an LSTM quickly overfits to the training tasks.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Zero-shot Generalization

Methods 이 논문이 사용한 방법론

Tanh Activation 설명 없음
Sigmoid Activation 설명 없음
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…

Similar Papers 제목 키워드 기반

Induce, Edit, Retrieve:Language Grounded Multimodal Schema for Instructional Video Retrieval

2021-11-17 · Yue Yang, Joongwon Kim, Artemis Panagopoulou, Mark Yatskar 외

Schemata are structured representations of complex tasks that can aid artificial intelligence by allowing models to break down complex tasks into intermediate steps. We propose a novel system that induces schemata from w…

RetrievalVideo Retrieval

Decidability and Undecidability Results for Propositional Schemata

2014-01-16 · Vincent Aravantinos, Ricardo Caferra, Nicolas Peltier

We define a logic of propositional formula schemata adding to the syntax of propositional logic indexed propositions and iterated connectives ranging over intervals parameterized by arithmetic variables. The satisfiabili…

A New Representation for Span-based CCG Parsing

2021-11-01 · EMNLP 2021 11 · Yoshihide Kato, Shigeki Matsubara

This paper proposes a new representation for CCG derivations. CCG derivations are represented as trees whose nodes are labeled with categories strictly restricted by CCG rule schemata. This characteristic is not suitable…

Interoperability and Customisation of Annotation Schemata in Argo

2014-05-01 · LREC 2014 5 · Rafal Rak, Jacob Carter, Andrew Rowley, Riza Theresa Batista-Navarro 외

The process of annotating text corpora involves establishing annotation schemata which define the scope and depth of an annotation task at hand. We demonstrate this activity in Argo, a Web-based workbench for the analysi…

Management

Machine learning as a model for cultural learning: Teaching an algorithm what it means to be fat

2020-03-24 · Alina Arseniev-Koehler, Jacob G. Foster

As we navigate our cultural environment, we learn cultural biases, like those around gender, social class, health, and body weight. It is unclear, however, exactly how public culture becomes private culture. In this pape…

ArticlesCultural Vocal Bursts Intensity PredictionLanguage ModellingNavigate+1