Non-monotonic Logical Reasoning Guiding Deep Learning for Explainable Visual Question Answering

09/23/2019
by   Heather Riley, et al.
16

State of the art algorithms for many pattern recognition problems rely on deep network models. Training these models requires a large labeled dataset and considerable computational resources. Also, it is difficult to understand the working of these learned models, limiting their use in some critical applications. Towards addressing these limitations, our architecture draws inspiration from research in cognitive systems, and integrates the principles of commonsense logical reasoning, inductive learning, and deep learning. In the context of answering explanatory questions about scenes and the underlying classification problems, the architecture uses deep networks for extracting features from images and for generating answers to queries. Between these deep networks, it embeds components for non-monotonic logical reasoning with incomplete commonsense domain knowledge, and for decision tree induction. It also incrementally learns and reasons with previously unknown constraints governing the domain's states. We evaluated the architecture in the context of datasets of simulated and real-world images, and a simulated robot computing, executing, and providing explanatory descriptions of plans. Experimental results indicate that in comparison with an “end to end” architecture of deep networks, our architecture provides better accuracy on classification problems when the training dataset is small, comparable accuracy with larger datasets, and more accurate answers to explanatory questions. Furthermore, incremental acquisition of previously unknown constraints improves the ability to answer explanatory questions, and extending non-monotonic logical reasoning to support planning and diagnostics improves the reliability and efficiency of computing and executing plans on a simulated robot.

READ FULL TEXT

page 7

page 14

page 18

page 19

research
01/25/2022

Combining Commonsense Reasoning and Knowledge Acquisition to Guide Deep Learning in Robotics

Algorithms based on deep network models are being used for many pattern ...
research
10/20/2020

Axiom Learning and Belief Tracing for Transparent Decision Making in Robotics

A robot's ability to provide descriptions of its decisions and beliefs p...
research
03/20/2015

The RatioLog Project: Rational Extensions of Logical Reasoning

Higher-level cognition includes logical reasoning and the ability of que...
research
03/19/2022

ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning

Charts are very popular for analyzing data. When exploring charts, peopl...
research
09/23/2019

Explainable High-order Visual Question Reasoning: A New Benchmark and Knowledge-routed Network

Explanation and high-order reasoning capabilities are crucial for real-w...
research
12/23/2020

Negation in Cognitive Reasoning

Negation is both an operation in formal logic and in natural language by...
research
07/31/2019

Towards a Theory of Intentions for Human-Robot Collaboration

The architecture described in this paper encodes a theory of intentions ...

Please sign up or login with your details

Forgot password? Click here to reset