6 citations · 12 across the 6 of their papers we have counts for
6 papers
JECC: Commonsense Reasoning Tasks Derived from Interactive Fictions
Mo Yu, Yi Gu, Xiaoxiao Guo +5
Commonsense reasoning simulates the human ability to make presumptions about our physical world, and it is an essential cornerstone in building general AI systems. We propose a new…
Combining Fast and Slow Thinking for Human-like and Efficient Navigation in Constrained Environments
Marianna B. Ganapini, Murray Campbell, Francesco Fabiano +8
Current AI systems lack several important human capabilities, such as adaptability, generalizability, self-control, consistency, common sense, and causal reasoning. We believe that…
Thinking Fast and Slow in AI: the Role of Metacognition
Marianna Bergamaschi Ganapini, Murray Campbell, Francesco Fabiano +7
AI systems have seen dramatic advancement in recent years, bringing many applications that pervade our everyday life. However, we are still mostly seeing instances of narrow AI: ma…
Circles are like Ellipses, or Ellipses are like Circles? Measuring the Degree of Asymmetry of Static and Contextual Embeddings and the Implications to Representation Learning
Wei Zhang, Murray Campbell, Yang Yu +1
Human judgments of word similarity have been a popular method of evaluating the quality of word embedding. But it fails to measure the geometry properties such as asymmetry. For ex…
Overcoming Catastrophic Forgetting via Direction-Constrained Optimization
Yunfei Teng, Anna Choromanska, Murray Campbell +3
This paper studies a new design of the optimization algorithm for training deep learning models with a fixed architecture of the classification network in a continual learning fram…
Text-based RL Agents with Commonsense Knowledge: New Challenges, Environments and Baselines
Keerthiram Murugesan, Mattia Atzeni, Pavan Kapanipathi +6
Text-based games have emerged as an important test-bed for Reinforcement Learning (RL) research, requiring RL agents to combine grounded language understanding with sequential deci…