Ken Forbus

IJCAI Conference 2023 Conference Paper

Sketch Recognition via Part-based Hierarchical Analogical Learning

• Kezhen Chen
• Ken Forbus
• Balaji Vasan Srinivasan
• Niyati Chhaya
• Madeline Usher

Sketch recognition has been studied for decades, but it is far from solved. Drawing styles are highly variable across people and adapting to idiosyncratic visual expressions requires data-efficient learning. Explainability also matters, so that users can see why a system got confused about something. This paper introduces a novel part-based approach for sketch recognition, based on hierarchical analogical learning, a new method to apply analogical learning to qualitative representations. Given a sketched object, our system automatically segments it into parts and constructs multi-level qualitative representations of them. Our approach performs analogical generalization at multiple levels of part descriptions and uses coarse-grained results to guide interpretation at finer levels. Experiments on the Berlin TU dataset and the Coloring Book Objects dataset show that the system can learn explainable models in a data-efficient manner.

AAAI Conference 2021 Conference Paper

Neural Analogical Matching

• Maxwell Crouse
• Constantine Nakos
• Ibrahim Abdelaziz
• Ken Forbus

Analogy is core to human cognition. It allows us to solve problems based on prior experience, it governs the way we conceptualize new information, and it even influences our visual perception. The importance of analogy to humans has made it an active area of research in the broader field of artificial intelligence, resulting in data-efficient models that learn and reason in human-like ways. While cognitive perspectives of analogy and deep learning have generally been studied independently of one another, the integration of the two lines of research is a promising step towards more robust and efficient learning techniques. As part of a growing body of research on such an integration, we introduce the Analogical Matching Network: a neural architecture that learns to produce analogies between structured, symbolic representations that are largely consistent with the principles of Structure-Mapping Theory.

AAAI Conference 2021 Conference Paper

Visual Relation Detection using Hybrid Analogical Learning

• Kezhen Chen
• Ken Forbus

Visual Relation Detection is currently one of the most popular problems for visual understanding. Many deep-learning models are designed for relation detection on images and have achieved impressive results. However, deep-learning models have several serious problems, including poor training-efficiency and lack of understandability. Psychologists have ample evidence that analogy is central in human learning and reasoning, including visual reasoning. This paper introduces a new hybrid system for visual relation detection combining deep-learning models and analogical generalization. Object bounding boxes and masks are detected using deep-learning models and analogical generalization over qualitative representations is used for visual relation detection between object pairs. Experiments on the Visual Relation Detection dataset indicates that our hybrid system gets comparable results on the task and is more training-efficient and explainable than pure deep-learning models.

AIJ Journal 2013 Journal Article

Exploiting persistent mappings in cross-domain analogical learning of physical domains

• Matthew Klenk
• Ken Forbus

Cross-domain analogies are a powerful method for learning new domains. This paper extends the Domain Transfer via Analogy (DTA) method with persistent mappings, correspondences between domains that are incrementally built up as a cognitive system gains experience with a new domain. DTA uses analogies between pairs of textbook example problems, or worked solutions, to create a domain mapping between a familiar and a new domain. This mapping enables the initialization of a new domain theory. Another analogy is then made between the domain theories themselves, providing additional conjectures about the new domain. After these conjectures are verified, the successful mappings are stored as persistent mappings to constrain future analogies between the domains. We show that DTA plus persistent mappings enables a Companion, the first structure mapping cognitive architecture, to learn the equation schemas and control knowledge necessary to solve problems in three domains (rotational mechanics, electricity, and heat) by analogy with linear mechanics. We provide a detailed analysis categorizing transfer failures. As with people, the most difficult step in cross-domain analogy is identifying an appropriate example. Once an analogous example has been found, DTA successfully transfers the domain knowledge necessary to solve the problem in the new domain 78% of the time. Furthermore, we illustrate how persistent mappings assist in retrieval of analogous examples and overcoming two types of mapping failures.

AIJ Journal 2009 Journal Article

Analogical model formulation for transfer learning in AP Physics

• Matthew Klenk
• Ken Forbus

Transfer learning is the ability to apply previously learned knowledge to new problems or domains. In qualitative reasoning, model formulation is the process of moving from the unruly, broad set of concepts used in everyday life to a concise, formal vocabulary of abstractions, assumptions, causal relationships, and models that support problem-solving. Approaching transfer learning from a model formulation perspective, we found that analogy with examples can be used to learn how to solve AP Physics style problems. We call this process analogical model formulation and implement it in the Companion cognitive architecture. A Companion begins with some basic mathematical skills, a broad common sense ontology, and some qualitative mechanics, but no equations. The Companion uses worked solutions, explanations of example problems at the level of detail appearing in textbooks, to learn what equations are relevant, how to use them, and the assumptions necessary to solve physics problems. We present an experiment, conducted by the Educational Testing Service, demonstrating that analogical model formulation enables a Companion to learn to solve AP Physics style problems. Across six different variations of relationships between base and target problems, or transfer levels, a Companion exhibited a 63% improvement in initial performance. While already a significant result, we describe an in-depth analysis of this experiment to pinpoint the causes of failures. Interestingly, the sources of failures were primarily due to errors in the externally generated problem and worked solution representations as well as some domain-specific problem-solving strategies, not analogical model formulation. To verify this, we describe a second experiment which was performed after fixing these problems. In this second experiment, a Companion achieved a 95. 8% improvement in initial performance due to transfer, which is nearly perfect. We know of no other problem-solving experiments which demonstrate performance of analogical learning over systematic variations of relationships between problems at this scale.

AAAI Conference 2008 Conference Paper

An Integrated Reasoning Approach to Moral Decision-Making

• Morteza Dehghani
• Ken Forbus

We present a computational model, MoralDM, which integrates several AI techniques in order to model recent psychological findings on moral decision-making. Current theories of moral decision-making extend beyond pure utilitarian models by relying on contextual factors that vary with culture. MoralDM uses a natural language system to produce formal representations from psychological stimuli, to reduce tailorability. The impacts of secular versus sacred values are modeled via qualitative reasoning, using an order of magnitude representation. MoralDM uses a combination of first-principles reasoning and analogical reasoning to determine consequences and utilities when making moral judgments. We describe how MoralDM works and show that it can model psychological results and improve its performance via accumulating examples.

AAAI Conference 2008 System Paper

CogSketch

• Ken Forbus
• Kate Lockwood
• Camillia Matuk

IJCAI Conference 1983 Conference Paper

Measurement Interpretation in Qualitative Process Theory

• Ken Forbus