Exploring Hierarchical Structure Representation in Transformer Models through Computational Mechanics
Olli Järviniemi, Udayanto Dwi Atmojo, Aayush Kucheria, Konsta Tiilikainen · Team Aalto EA
Submitted to Computational Mechanics Hackathon. Sprint projects are early-stage work by participants, not Apart Research publications.
This work attempts to explore how an approach based on computational mechanics can cope when a more complex hierarchical generative process is involved, i.e, a process that comprises Hidden Markov Models (HMMs) whose transition probabilities change over time.
We find that small transformer models are capable of modeling such changes in an HMM. However, our preliminary investigations did not find geometrically represented probabilities for different hypotheses.
Reviews
No public critique yet.
Cite this project
@misc{jarviniemi2024exploring,
title = {{Exploring Hierarchical Structure Representation in Transformer Models through Computational Mechanics}},
author = {Olli Järviniemi and Udayanto Dwi Atmojo and Aayush Kucheria and Konsta Tiilikainen},
year = {2024},
month = jun,
note = {Submitted to Computational Mechanics Hackathon, an Apart Research Sprint},
howpublished = {\url{https://apartresearch.com/sprints/projects/exploring-hierarchical-structure-representation-in-transformer-models-through-computational-mechanics}},
url = {https://apartresearch.com/sprints/projects/exploring-hierarchical-structure-representation-in-transformer-models-through-computational-mechanics}
}More from Computational Mechanics Hackathon
- View project: Unsupervised Recovery of Hidden Markov Models from Transformers with Evolutionary Algorithms
Unsupervised Recovery of Hidden Markov Models from Transformers with Evolutionary Algorithms
Stargazy Pie
Prior work finds that transformer neural networks trained to mimic the output of a Hidden Markov Model (HMM) embed the optimal Bayesian beliefs for the HMM's current state in their residual stream, which can be …
- View project: Looking forward to posterity: what past information is transferred to the future?
Looking forward to posterity: what past information is transferred to the future?
Nonkansa
I used mechanistic interpretability techniques to try to see what information the provided Random Randox XOR transformer looks at when making predictions by examining its attention heads manually. I find that earlier …
- View project: Investigating the Effect of Model Capacity Constraints on Belief State Representations
Investigating the Effect of Model Capacity Constraints on Belief State Representations
Studying Generalization and Abstraction
Computational mechanics provides a formal framework for understanding the concepts needed to perform optimal prediction. Abstraction and generalization seem core to the function of intelligent systems, but are not yet …