From Neurons to Neutrons: A Case Study in Interpretability

• URL: http://arxiv.org/abs/2405.17425v1
• Date: Mon, 27 May 2024 17:59:35 GMT
• Title: From Neurons to Neutrons: A Case Study in Interpretability
• Authors: Ouail Kitouni, Niklas Nolte, Víctor Samuel Pérez-Díaz, Sokratis Trifinopoulos, Mike Williams,
• Abstract summary: We argue that high-dimensional neural networks can learn low-dimensional representations of their training data that are useful beyond simply making good predictions. This indicates that such approaches to interpretability can be useful for deriving a new understanding of a problem from models trained to solve it.
• Score: 5.242869847419834
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Mechanistic Interpretability (MI) promises a path toward fully understanding how neural networks make their predictions. Prior work demonstrates that even when trained to perform simple arithmetic, models can implement a variety of algorithms (sometimes concurrently) depending on initialization and hyperparameters. Does this mean neuron-level interpretability techniques have limited applicability? We argue that high-dimensional neural networks can learn low-dimensional representations of their training data that are useful beyond simply making good predictions. Such representations can be understood through the mechanistic interpretability lens and provide insights that are surprisingly faithful to human-derived domain knowledge. This indicates that such approaches to interpretability can be useful for deriving a new understanding of a problem from models trained to solve it. As a case study, we extract nuclear physics concepts by studying models trained to reproduce nuclear data.

Related papers

• Automated Natural Language Explanation of Deep Visual Neurons with Large Models [43.178568768100305]
  This paper proposes a novel post-hoc framework for generating semantic explanations of neurons with large foundation models. Our framework is designed to be compatible with various model architectures and datasets, automated and scalable neuron interpretation.
  arXiv  Detail & Related papers  (2023-10-16T17:04:51Z)
• Adversarial Attacks on the Interpretation of Neuron Activation Maximization [70.5472799454224]
  Activation-maximization approaches are used to interpret and analyze trained deep-learning models. In this work, we consider the concept of an adversary manipulating a model for the purpose of deceiving the interpretation.
  arXiv  Detail & Related papers  (2023-06-12T19:54:33Z)
• Utility-Probability Duality of Neural Networks [4.871730595406078]
  We propose an alternative utility-based explanation to the standard supervised learning procedure in deep learning. The basic idea is to interpret the learned neural network not as a probability model but as an ordinal utility function. We show that for all neural networks with softmax outputs, the SGD learning dynamic of maximum likelihood estimation can be seen as an iteration process.
  arXiv  Detail & Related papers  (2023-05-24T08:09:07Z)
• On Modifying a Neural Network's Perception [3.42658286826597]
  We propose a method which allows one to modify what an artificial neural network is perceiving regarding specific human-defined concepts. We test the proposed method on different models, assessing whether the performed manipulations are well interpreted by the models, and analyzing how they react to them.
  arXiv  Detail & Related papers  (2023-03-05T12:09:37Z)
• Interpretable Self-Aware Neural Networks for Robust Trajectory Prediction [50.79827516897913]
  We introduce an interpretable paradigm for trajectory prediction that distributes the uncertainty among semantic concepts. We validate our approach on real-world autonomous driving data, demonstrating superior performance over state-of-the-art baselines.
  arXiv  Detail & Related papers  (2022-11-16T06:28:20Z)
• Searching for the Essence of Adversarial Perturbations [73.96215665913797]
  We show that adversarial perturbations contain human-recognizable information, which is the key conspirator responsible for a neural network's erroneous prediction. This concept of human-recognizable information allows us to explain key features related to adversarial perturbations.
  arXiv  Detail & Related papers  (2022-05-30T18:04:57Z)
• EINNs: Epidemiologically-Informed Neural Networks [75.34199997857341]
  We introduce a new class of physics-informed neural networks-EINN-crafted for epidemic forecasting. We investigate how to leverage both the theoretical flexibility provided by mechanistic models as well as the data-driven expressability afforded by AI models.
  arXiv  Detail & Related papers  (2022-02-21T18:59:03Z)
• Data-driven emergence of convolutional structure in neural networks [83.4920717252233]
  We show how fully-connected neural networks solving a discrimination task can learn a convolutional structure directly from their inputs. By carefully designing data models, we show that the emergence of this pattern is triggered by the non-Gaussian, higher-order local structure of the inputs.
  arXiv  Detail & Related papers  (2022-02-01T17:11:13Z)
• Explainable artificial intelligence for mechanics: physics-informing neural networks for constitutive models [0.0]
  In mechanics, the new and active field of physics-informed neural networks attempts to mitigate this disadvantage by designing deep neural networks on the basis of mechanical knowledge. We propose a first step towards a physics-forming-in approach, which explains neural networks trained on mechanical data a posteriori. Therein, the principal component analysis decorrelates the distributed representations in cell states of RNNs and allows the comparison to known and fundamental functions.
  arXiv  Detail & Related papers  (2021-04-20T18:38:52Z)
• The Neural Coding Framework for Learning Generative Models [91.0357317238509]
  We propose a novel neural generative model inspired by the theory of predictive processing in the brain. In a similar way, artificial neurons in our generative model predict what neighboring neurons will do, and adjust their parameters based on how well the predictions matched reality.
  arXiv  Detail & Related papers  (2020-12-07T01:20:38Z)
• Bayesian Neural Networks [0.0]
  We show how errors in prediction by neural networks can be obtained in principle, and provide the two favoured methods for characterising these errors. We will also describe how both of these methods have substantial pitfalls when put into practice.
  arXiv  Detail & Related papers  (2020-06-02T09:43:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.