2 citations · 4 across the 8 of their papers we have counts for
10 papers
Do Quantum Models Scale Like LLMs?
David S. Berman, Ying-Jer Kao, Roger G. Melko +1
In this work, we study the neural scaling laws of RydbergGPT, an autoregressive transformer model trained on qubit projective measurement data gathered from interacting Rydberg ato…
Optimal Pruning for Neural Architectures using Fisher Information Distances
David S. Berman, Yen-Yu Fu, Edward Hirst +1
A new scheme for parameter pruning is introduced, derived from the differential-geometric distance in model space. Pruning a parameter sets its value to zero, representing a displa…
AI and the Research-Education Environment of Physics
Savannah Thais, Koji Hashimoto, David S. Berman +6
In the current era of AI transforming the research-education environment of physics, variety of issues and concerns arise. The KITP program "Generative AI for High and Low Energy P…
Towards Worst-Case Guarantees with Scale-Aware Interpretability
Lauren Greenspan, David Berman, Aryeh Brill +9
Neural networks organize information according to the hierarchical, multi-scale structure of natural data. Methods to interpret model internals should be similarly scale-aware, exp…
A path to natural language through tokenisation and transformers
David S. Berman, Alexander G. Stapleton
Natural languages exhibit striking regularities in their statistical structure, including notably the emergence of Zipf's and Heaps' laws. Despite this, it remains broadly unclear…
Modeling financial time series with quantum field theory
Dimitrios Bachtis, David S. Berman, Arabella Schelpe
We use a quantum field theory with inhomogeneous couplings and explicit symmetry-breaking to model an ensemble of financial time series from the SP 500 index. The conti…
Teaming LLMs to Detect and Mitigate Hallucinations
Demian Till, John Smeaton, Peter Haubrick +3
Recent work has demonstrated state-of-the-art results in large language model (LLM) hallucination detection and mitigation through consistency-based approaches which involve aggreg…
Grokking vs. Learning: Same Features, Different Encodings
Dmitry Manning-Coe, Jacopo Gliozzi, Alexander G. Stapleton +4
Grokking typically achieves similar loss to ordinary, "steady", learning. We ask whether these different learning paths - grokking versus ordinary training - lead to fundamental di…
Explainable AI: Definition and attributes of a good explanation for health AI
Evangelia Kyrimi, Scott McLachlan, Jared M Wohlgemut +4
Proposals of artificial intelligence (AI) solutions based on increasingly complex and accurate predictive models are becoming ubiquitous across many disciplines. As the complexity…
NCoder -- A Quantum Field Theory approach to encoding data
David S. Berman, Marc S. Klinger, Alexander G. Stapleton
In this paper we present a novel approach to interpretable AI inspired by Quantum Field Theory (QFT) which we call the NCoder. The NCoder is a modified autoencoder neural network w…