Search Results for author:
Found 19 papers, 3 papers with code
An Ambiguity Measure for Recognizing the Unknowns in Deep Learning
We define the ambiguity based on the geometric arrangements of the decision boundaries and the convex hull of training set in the feature space learned by the trained model, and demonstrate that a single ambiguity measure may detect a considerable portion of mistakes of a model on in-distribution samples, adversarial inputs, as well as out-of-distribution inputs.
Large Language Models' Understanding of Math: Source Criticism and Extrapolation
We also see that GPT-4's ability to prove mathematical theorems is continuously expanding over time despite the claim that it is a fixed model.
Should Machine Learning Models Report to Us When They Are Clueless?
The right to AI explainability has consolidated as a consensus in the research community and policy-making.
Over-parameterization: A Necessary Condition for Models that Extrapolate
Partitions are defined by decision boundaries and so is the classification model/function.
Deep Learning Generalization, Extrapolation, and Over-parameterization
We show that interpolation is not adequate to understand generalization of deep networks and we should broaden our perspective.
Decision boundaries and convex hulls in the feature space that deep learning functions learn from images
We study the partitioning of the domain in feature space, identify regions guaranteed to have certain classifications, and investigate its implications for the pixel space.
To what extent should we trust AI models when they extrapolate?
Given a model trained to recommend clinical procedures for patients, can we trust the recommendation when the model considers a patient older or younger than all the samples in the training set?
Community Detection in Medical Image Datasets: Using Wavelets and Spectral Methods
Medical image datasets can have large number of images representing patients with different health conditions and various disease severity.
A Homotopy Algorithm for Optimal Transport
We define the homotopy path as a subspace rotation based on the orthogonal Procrustes problem, and then we discretize the homotopy path using eigenvalue decomposition of the rotation matrix.
Extrapolation Frameworks in Cognitive Psychology Suitable for Study of Image Classification Models
In our framework, we use the term extrapolation in this specific way of extrapolating outside the convex hull of training set (in the pixel space or feature space) but within the specific scope defined by the training data, the same way extrapolation is defined in many studies in cognitive science.
Federated Learning without Revealing the Decision Boundaries
We explain that those mixed images will be samples on the decision boundaries of the trained model, and although such methods successfully hide the contents of images from the entity in charge of federated learning, they provide crucial information to that entity about the decision boundaries of the trained model.
A Sketching Method for Finding the Closest Point on a Convex Hull
However, solving the problem using standard optimization algorithms can be very expensive for large datasets.
Deep Learning Generalization and the Convex Hull of Training Sets
We study the generalization of deep learning models in relation to the convex hull of their training sets.
Using Wavelets and Spectral Methods to Study Patterns in Image-Classification Datasets
We show that each image can be written as the summation of a finite number of rank-1 patterns in the wavelet space, providing a low rank approximation that captures the structures and patterns essential for learning.
Using Wavelets to Analyze Similarities in Image-Classification Datasets
We show that such analysis can provide valuable insights about the datasets and the classification task at hand, prior to training a model.
Auditing and Debugging Deep Learning Models via Decision Boundaries: Individual-level and Group-level Analysis
Here, we use flip points to accomplish these goals for deep learning models with continuous output scores (e. g., computed by softmax), used in social applications.
Investigating Decision Boundaries of Trained Neural Networks
Through numerical results, we confirm that some of the speculations about the decision boundaries are accurate, some of the computational methods can be improved, and some of the simplifying assumptions may be unreliable, for models with nonlinear activation functions.
Refining the Structure of Neural Networks Using Matrix Conditioning
Here, we propose a practical method that employs matrix conditioning to automatically design the structure of layers of a feed-forward network, by first adjusting the proportion of neurons among the layers of a network and then scaling the size of network up or down.
Interpreting Neural Networks Using Flip Points
We show that distance between an input and the closest flip point identifies the most influential points in the training data.
