Papers for

cognitive system developers

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Fast analogy engine improves aligning complex relational structures

SMTB: Fast Structure-Mapping with Tight Bounds

Abstract: Structure-mapping forms analogies by aligning systems of relationally connected elements based on shared structure instead of surface features. We introduce a new structure-mapping algorithm: Structure-Mapping with Tight Bounds (SMTB) that is 5--15x faster than the structure-mapping engine (SME) and about 50\% better at finding mappings in large nested domains. SMTB is part of the broader Cognitive Rule Engine (CRE) project, a flexible multi-language-compatible framework with an accessible Python interface to state-of-the-art C++ implementations of core algorithms commonly used in cognitive systems such as pattern matching, planning, and structure-mapping. CRE and SMTB are designed to work with a wide range of representation choices. Unlike SME, which biases higher-order correspondences in tree-like predicate logic, SMTB maximizes relational connectivity without privileging higher-order relations. This allows SMTB to work just as well over arbitrary relational graphs as it does in tree-like domains of nested predicate logic. We discuss situations where privileging "higher-orderness" in structure-mapping can cause issues, and illustrate how SMTB avoids failure modes that SME would encounter in these situations. We also provide an evaluation comparing SMTB to SME v4 over 5845 domain pairs from the SME corpus.

Tue 22 SeptArtificial Intelligence
The gist
Comparing complex systems based on their structure rather than surface details is hard and often slow. The authors developed a method called SMTB that finds these structural similarities up to 15 times faster and works better with complicated nested structures than the previous standard. Unlike the older method, SMTB doesn’t focus only on certain types of relationships, making it more flexible for different kinds of data. This new approach helps avoid errors that older methods might make in tricky situations. The authors tested SMTB on thousands of examples and showed its advantages clearly.
Open → 2609.25508v1

Diffusion models reveal how humans form concept hierarchies naturally

Diffusion Models and Concept Formation

Abstract: Humans organize knowledge into a taxonomy of concepts with nested levels of abstraction and a \emph{basic level} at which people recognize and name objects with the least cognitive effort. Cobweb is a classic cognitive account of this ability, an incremental learner that builds a probabilistic concept hierarchy by maximizing category utility. We argue that diffusion models, although designed for image synthesis, implicitly perform the same computation. The noisy marginals of a diffusion model are Gaussian smoothings of the data distribution, and the modes of these marginals form a hierarchy that corresponds to a Cobweb tree of probabilistic prototypes in four respects. Both are hierarchical density models, both are hierarchical-Bayesian models with Gaussian prototypes, both treat categorization as score-following that reduces uncertainty, and in both a basic level emerges. We locate this basic level for a diffusion model at an intermediate noise level, where recent analyses show that the reverse process commits to the class identity of a sample. The two models differ mainly in how they represent and learn the taxonomy. Cobweb learns a discrete tree incrementally, whereas a diffusion model encodes a continuous, interpolable hierarchy in a single learned score field fit to the data distribution. We test the correspondence on MNIST and Fashion-MNIST by recovering the diffusion hierarchy through mode-finding and comparing the basic levels of the two models. This reframes diffusion as a cognitive model of concept formation and offers Cobweb a continuous, scalable instantiation.

Fri 11 SeptArtificial IntelligenceMachine Learning
The gist
People organize what they know into groups and subgroups, like sorting animals into categories. The authors show that diffusion models, originally designed to generate images, can also create similar category trees by smoothing data and finding natural groupings. These models automatically form a basic level of concepts where recognition is easiest, just like humans do. They compared this idea using simple image datasets and found the two approaches share important features but handle learning differently.
Open → 2609.13047v1