Search Results for author:
Found 10 papers, 6 papers with code
Towards a geometric understanding of Spatio Temporal Graph Convolution Networks
In this paper, we first propose to use a local Dataset Graph (DS-Graph) obtained from the feature representation of input data at each layer to develop an understanding of the layer-wise embedding geometry of the STGCN.
Characterizing Large Language Model Geometry Solves Toxicity Detection and Generation
We obtain in closed form (i) the intrinsic dimension in which the Multi-Head Attention embeddings are constrained to exist and (ii) the partition and per-region affine mappings of the per-layer feedforward networks.
Study of Manifold Geometry using Multiscale Non-Negative Kernel Graphs
Modern machine learning systems are increasingly trained on large amounts of data embedded in high-dimensional spaces.
The Geometry of Self-supervised Learning Models and its Impact on Transfer Learning
Self-supervised learning (SSL) has emerged as a desirable paradigm in computer vision due to the inability of supervised models to learn representations that can generalize in domains with limited labels.
Channel redundancy and overlap in convolutional neural networks with channel-wise NNK graphs
Feature spaces in the deep layers of convolutional neural networks (CNNs) are often very high-dimensional and difficult to interpret.
NNK-Means: Data summarization using dictionary learning with non-negative kernel regression
An increasing number of systems are being designed by gathering significant amounts of data and then optimizing the system parameters directly using the obtained data.
Channel-Wise Early Stopping without a Validation Set via NNK Polytope Interpolation
Motivated by our observations, we use CW-DeepNNK to propose a novel early stopping criterion that (i) does not require a validation set, (ii) is based on a task performance metric, and (iii) allows stopping to be reached at different points for each channel.
DeepNNK: Explaining deep models and their generalization using polytope interpolation
Modern machine learning systems based on neural networks have shown great success in learning complex data patterns while being able to make good predictions on unseen data points.
BIG-bench Machine Learning
Interpretability Techniques for Deep Learning
+2
Efficient graph construction for image representation
Graphs are useful to interpret widely used image processing methods, e. g., bilateral filtering, or to develop new ones, e. g., kernel based techniques.
Neighborhood and Graph Constructions using Non-Negative Kernel Regression
Data-driven neighborhood definitions and graph constructions are often used in machine learning and signal processing applications.
