Paper Summary: Contrastive Learning of Structured World Models
Abstract: A structured understanding of our world in terms of objects, relations, and hierarchies is an important component of human cognition. Learning such a structured world model from raw sensory data remains a challenge. As a step towards this goal, we introduce Contrastively-trained Structured World Models (C-SWMs). CSWMs utilize a contrastive approach for representation learning i...
Paper Summary: Learning Explanatory Rules from Noisy Data
Abstract: Artificial Neural Networks are powerful function approximators capable of modeling solutions to a wide variety of problems, both supervised and unsupervised. As their size and expressivity increase, so too does the variance of the model, yielding a nearly ubiquitous overfitting problem. Although mitigated by a variety of model regularisation methods, the common cure is to seek ...
Paper Summary: Neural Logic Machines
Abstract: We propose the Neural Logic Machine (NLM), a neural-symbolic architecture for both inductive learning and logic reasoning. NLMs exploit the power of both neural networks---as function approximators, and logic programming---as a symbolic processor for objects with properties, relations, logic connectives, and quantifiers. After being trained on small-scale tasks (such as sorting...
Paper Summary: Neural Logic Reinforcement Learning
Abstract: Deep reinforcement learning (DRL) has achieved significant breakthroughs in various tasks. However, most DRL algorithms suffer a problem of generalizing the learned policy, which makes the policy performance largely affected even by minor modifications of the training environment. Except that, the use of deep neural networks makes the learned policies hard to be interpretable. ...