Connecting Concept Convexity and Human-Machine Alignment in Deep Neural Networks
- URL: http://arxiv.org/abs/2409.06362v1
- Date: Tue, 10 Sep 2024 09:32:16 GMT
- Title: Connecting Concept Convexity and Human-Machine Alignment in Deep Neural Networks
- Authors: Teresa Dorszewski, Lenka Tětková, Lorenz Linhardt, Lars Kai Hansen,
- Abstract summary: Understanding how neural networks align with human cognitive processes is a crucial step toward developing more interpretable and reliable AI systems.
We identify a correlation between these two dimensions that reflect the similarity relations humans in cognitive tasks.
This presents a first step toward understanding the relationship convexity between human-machine alignment.
- Score: 3.001674556825579
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Understanding how neural networks align with human cognitive processes is a crucial step toward developing more interpretable and reliable AI systems. Motivated by theories of human cognition, this study examines the relationship between \emph{convexity} in neural network representations and \emph{human-machine alignment} based on behavioral data. We identify a correlation between these two dimensions in pretrained and fine-tuned vision transformer models. Our findings suggest that the convex regions formed in latent spaces of neural networks to some extent align with human-defined categories and reflect the similarity relations humans use in cognitive tasks. While optimizing for alignment generally enhances convexity, increasing convexity through fine-tuning yields inconsistent effects on alignment, which suggests a complex relationship between the two. This study presents a first step toward understanding the relationship between the convexity of latent representations and human-machine alignment.
Related papers
- Exploring neural oscillations during speech perception via surrogate gradient spiking neural networks [59.38765771221084]
We present a physiologically inspired speech recognition architecture compatible and scalable with deep learning frameworks.
We show end-to-end gradient descent training leads to the emergence of neural oscillations in the central spiking neural network.
Our findings highlight the crucial inhibitory role of feedback mechanisms, such as spike frequency adaptation and recurrent connections, in regulating and synchronising neural activity to improve recognition performance.
arXiv Detail & Related papers (2024-04-22T09:40:07Z) - Evaluating alignment between humans and neural network representations in image-based learning tasks [5.657101730705275]
We tested how well the representations of $86$ pretrained neural network models mapped to human learning trajectories.
We found that while training dataset size was a core determinant of alignment with human choices, contrastive training with multi-modal data (text and imagery) was a common feature of currently publicly available models that predicted human generalisation.
In conclusion, pretrained neural networks can serve to extract representations for cognitive models, as they appear to capture some fundamental aspects of cognition that are transferable across tasks.
arXiv Detail & Related papers (2023-06-15T08:18:29Z) - Language Knowledge-Assisted Representation Learning for Skeleton-Based
Action Recognition [71.35205097460124]
How humans understand and recognize the actions of others is a complex neuroscientific problem.
LA-GCN proposes a graph convolution network using large-scale language models (LLM) knowledge assistance.
arXiv Detail & Related papers (2023-05-21T08:29:16Z) - Human alignment of neural network representations [22.671101285994013]
We investigate the factors that affect the alignment between the representations learned by neural networks and human mental representations inferred from behavioral responses.
We find that model scale and architecture have essentially no effect on the alignment with human behavioral responses.
We find that some human concepts such as food and animals are well-represented by neural networks whereas others such as royal or sports-related objects are not.
arXiv Detail & Related papers (2022-11-02T15:23:16Z) - The world seems different in a social context: a neural network analysis
of human experimental data [57.729312306803955]
We show that it is possible to replicate human behavioral data in both individual and social task settings by modifying the precision of prior and sensory signals.
An analysis of the neural activation traces of the trained networks provides evidence that information is coded in fundamentally different ways in the network in the individual and in the social conditions.
arXiv Detail & Related papers (2022-03-03T17:19:12Z) - 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) - A neural anisotropic view of underspecification in deep learning [60.119023683371736]
We show that the way neural networks handle the underspecification of problems is highly dependent on the data representation.
Our results highlight that understanding the architectural inductive bias in deep learning is fundamental to address the fairness, robustness, and generalization of these systems.
arXiv Detail & Related papers (2021-04-29T14:31:09Z) - Learning Interpretable Models for Coupled Networks Under Domain
Constraints [8.308385006727702]
We investigate the idea of coupled networks by focusing on interactions between structural edges and functional edges of brain networks.
We propose a novel formulation to place hard network constraints on the noise term while estimating interactions.
We validate our method on multishell diffusion and task-evoked fMRI datasets from the Human Connectome Project.
arXiv Detail & Related papers (2021-04-19T06:23:31Z) - On 1/n neural representation and robustness [13.491651740693705]
We show that imposing the experimentally observed structure on artificial neural networks makes them more robust to adversarial attacks.
Our findings complement the existing theory relating wide neural networks to kernel methods.
arXiv Detail & Related papers (2020-12-08T20:34:49Z) - Learning Connectivity of Neural Networks from a Topological Perspective [80.35103711638548]
We propose a topological perspective to represent a network into a complete graph for analysis.
By assigning learnable parameters to the edges which reflect the magnitude of connections, the learning process can be performed in a differentiable manner.
This learning process is compatible with existing networks and owns adaptability to larger search spaces and different tasks.
arXiv Detail & Related papers (2020-08-19T04:53:31Z)
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.