Search Results for author:
Found 7 papers, 2 papers with code
Formalising Concepts as Grounded Abstractions
The mathematics of partial orders and lattices is a standard tool for modelling conceptual spaces (Ch. 2, Mitchell (1997), Ganter and Obiedkov (2016)); however, there is no formal work that we are aware of which defines a conceptual lattice on top of a representation that is induced using unsupervised deep learning (Goodfellow et al., 2016).
Neural Variational Inference For Estimating Uncertainty in Knowledge Graph Embeddings
Recent advances in Neural Variational Inference allowed for a renaissance in latent variable models in a variety of domains involving high-dimensional data.
COBRA: Data-Efficient Model-Based RL through Unsupervised Object Discovery and Curiosity-Driven Exploration
Data efficiency and robustness to task-irrelevant perturbations are long-standing challenges for deep reinforcement learning algorithms.
Scalable Neural Theorem Proving on Knowledge Bases and Natural Language
Reasoning over text and Knowledge Bases (KBs) is a major challenge for Artificial Intelligence, with applications in machine reading, dialogue, and question answering.
Towards Neural Theorem Proving at Scale
Neural models combining representation learning and reasoning in an end-to-end trainable manner are receiving increasing interest.
SCAN: Learning Hierarchical Compositional Visual Concepts
SCAN learns concepts through fast symbol association, grounding them in disentangled visual primitives that are discovered in an unsupervised manner.
