6 papers
Agentic Chunking and Bayesian De-chunking of AI Generated Fuzzy Cognitive Maps: A Model of the Thucydides Trap
Akash Kumar Panda, Olaoluwa Adigun, Bart Kosko
We automatically generate feedback causal fuzzy cognitive maps (FCMs) from text by teaching large-language-model agents to break the text into overlapping chunks of text. Convex mi…
The Agentic Leash: Extracting Causal Feedback Fuzzy Cognitive Maps with LLMs
Akash Kumar Panda, Olaoluwa Adigun, Bart Kosko
We design a large-language-model (LLM) agent system that extracts causal feedback fuzzy cognitive maps (FCMs) from raw text. The causal learning or extraction process is agentic bo…
Causal Autoencoder-like Generation of Feedback Fuzzy Cognitive Maps with an LLM Agent
Akash Kumar Panda, Olaoluwa Adigun, Bart Kosko
A large language model (LLM) can map a feedback causal fuzzy cognitive map (FCM) into text and then reconstruct the FCM from the text. This explainable AI system approximates an id…
Soft Diamond Regularizers for Deep Learning
Olaoluwa Adigun, Bart Kosko
This chapter presents the new family of soft diamond synaptic regularizers based on thick-tailed symmetric alpha stable probability bell curves. These new parametrized weigh…
Bidirectional Variational Autoencoders
Bart Kosko, Olaoluwa Adigun
We present the new bidirectional variational autoencoder (BVAE) network architecture. The BVAE uses a single neural network both to encode and decode instead of an encoder-decoder…
Controlled Causal Hallucinations Can Estimate Phantom Nodes in Multiexpert Mixtures of Fuzzy Cognitive Maps
Akash Kumar Panda, Bart Kosko
An adaptive multiexpert mixture of feedback causal models can approximate missing or phantom nodes in large-scale causal models. The result gives a scalable form of \emph{big knowl…