Search Results for author:
Found 13 papers, 5 papers with code
Understanding the Inner Workings of Language Models Through Representation Dissimilarity
As language models are applied to an increasing number of real-world applications, understanding their inner workings has become an important issue in model trust, interpretability, and transparency.
Attributing Learned Concepts in Neural Networks to Training Data
By now there is substantial evidence that deep learning models learn certain human-interpretable features as part of their internal representations of data.
Impact of architecture on robustness and interpretability of multispectral deep neural networks
At one extreme, known as "early fusion," additional bands are stacked as extra channels to obtain an input image with more than three channels.
Neural Image Compression: Generalization, Robustness, and Spectral Biases
Our benchmarks, spectral inspection tools, and findings provide a crucial bridge to the real-world adoption of NIC.
Quantifying the robustness of deep multispectral segmentation models against natural perturbations and data poisoning
In this work, we seek to characterize the performance and robustness of a multispectral (RGB and near infrared) image segmentation model subjected to adversarial attacks and natural perturbations.
How many dimensions are required to find an adversarial example?
Past work exploring adversarial vulnerability have focused on situations where an adversary can perturb all dimensions of model input.
Fast computation of permutation equivariant layers with the partition algebra
The space of permutation equivariant linear layers is a generalization of the partition algebra, an object first discovered in statistical physics with deep connections to the representation theory of the symmetric group, and the basis described above generalizes the so-called orbit basis of the partition algebra.
Edit at your own risk: evaluating the robustness of edited models to distribution shifts
The current trend toward ever-larger models makes standard retraining procedures an ever-more expensive burden.
Exploring the Representation Manifolds of Stable Diffusion Through the Lens of Intrinsic Dimension
We find that choice of prompt has a substantial impact on the intrinsic dimension of representations at both layers of the model which we explored, but that the nature of this impact depends on the layer being considered.
Internal Representations of Vision Models Through the Lens of Frames on Data Manifolds
While the last five years have seen considerable progress in understanding the internal representations of deep learning models, many questions remain.
Testing predictions of representation cost theory with CNNs
It is widely acknowledged that trained convolutional neural networks (CNNs) have different levels of sensitivity to signals of different frequency.
On the Symmetries of Deep Learning Models and their Internal Representations
In this paper we seek to connect the symmetries arising from the architecture of a family of models with the symmetries of that family's internal representation of data.
Fiber Bundle Morphisms as a Framework for Modeling Many-to-Many Maps
That is, a single input can potentially yield many different outputs (whether due to noise, imperfect measurement, or intrinsic stochasticity in the process) and many different inputs can yield the same output (that is, the map is not injective).
