You can also find my articles on my Google Scholar profile.
Published in arXiv Preprints, 2024
The advancement of large language models (LLMs) for real-world applications hinges critically on enhancing their reasoning capabilities. In this work, we explore the reasoning abilities of large language models (LLMs) through their geometrical understanding. Read more
Published in International Conference on Machine Learning (ICML), 2024
Large Language Models~(LLMs) drive current AI breakthroughs despite very little being known about their internal representations, e.g., how to extract a few informative features to solve various downstream tasks. To provide a practical and principled answer, we propose to characterize LLMs from a geometric perspective. Read more
Published in IEEE Open Journal of Signal Processing, 2024
Spatio-temporal graph convolutional networks (STGCNs) have emerged as a desirable model for many applications including skeleton-based human action recognition. Despite achieving state-of-the-art performance, our limited understanding of the representations learned by these models hinders their application in critical and real-world settings. Read more
Published in International Workshop on Mining and Learning with Graphs, Conference on Knowledge Discovery and Data Mining (KDD), 2023
Recent works, such as GRALE, have focused on the semi-supervised setting to learn an optimal similarity function for constructing a task-optimal graph. However, in many scenarios with billions of data points and trillions of potential edges, the run-time and computational requirements for training the similarity model make these approaches impractical. In this work, we consider data sampling as a means to overcome this issue. Read more
Published in Graph Signal Processing Workshop 2023, 2023
Deep learning approaches have achieved unprecedented performance success in many application domains. In this work, we first present an empirical framework for studying deep learning by characterizing the geometry of the data manifold in the embedding spaces, using computationally efficient graph-based methods to learn manifold properties. Read more
Published in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022
Modern machine learning systems are increasingly trained on large amounts of data embedded in high-dimensional spaces. Often this is done without analyzing the structure of the dataset. In this work, we propose a framework to study the geometric structure of the data. Read more
Published in arXiv Preprints, 2022
The recent popularity of SSL has led to the development of several models that make use of diverse training strategies, architectures, and data augmentation policies with no existing unified framework to study or assess their effectiveness in transfer learning. Read more
Published in IEEE 30th European Signal Processing Conference (EUSIPCO), 2022
An increasing number of systems are being designed by first gathering significant amounts of data, and then optimizing the system parameters directly using the obtained data. Often this is done without analyzing the dataset structure. Read more
Published in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022
Feature spaces in the deep layers of convolutional neural networks (CNNs) are often very high-dimensional and difficult to interpret. However, convolutional layers consist of multiple channels that are activated by different types of inputs, which suggests that more insights may be gained by studying the channels Read more
Published in Asia Pacific Signal and Information Processing Association (APSIPA), 2021
Convolutional neural networks (ConvNets) comprise high-dimensional feature spaces formed by the aggregation of multiple channels, where analyzing intermediate data representations and the model's evolution can be challenging owing to the curse of dimensionality. We present channel-wise DeepNNK (CW-DeepNNK) Read more
Published in Asilomar Conference on Signals, Systems, and Computers , 2021
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. However, the limited understanding of these systems hinders further progress and application to several domains in the real world. Read more
Published in IEEE Data Science and Learning Workshop (DSLW), 2021
Several machine learning methods leverage the idea of locality by using $k$-nearest neighbor (KNN) techniques to design better pattern recognition models. However, the choice of KNN parameters such as $k$ is often made experimentally, e.g., via cross-validation, leading to local neighborhoods without a clear geometric interpretation. Read more
Best student paper Published in IEEE International Conference on Image Processing (ICIP), 2020
Graphs are useful to interpret widely used image processing methods, e.g., bilateral filtering, or to develop new ones, e.g., kernel based techniques. However, simple graph constructions are often used, where edge weight and connectivity depend on a few parameters. In particular, the sparsity of the graph is determined by the choice of a window size. Read more
Published in IEEE International Workshop on Multimedia Signal Processing (MMSP), 2020
While deep learning is a powerful tool for manyapplications, there has been only limited research about selectionof data for training, i.e., instance selection, which enhances deeplearning scalability by saving computational resources. Read more
Published in arXiv Preprints, 2020
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. However, the limited interpretability of these systems hinders further progress and application to several domains in the real world. Read more
Published in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020
Data driven graph constructions are often used in machine learning applications. However, learning an optimal graph from data is still a challenging task. K-nearest neighbor and ϵ-neighborhood methods are among the most common graph construction methods, due to their computational simplicity, but the choice of parameters such as K and ϵ associated with these methods is often ad hoc and lacks a clear interpretation. Read more
Published in Under review (IEEE Transactions on Pattern Analysis and Machine Intelligence) , 2019
Data driven graph constructions are often used in various applications, including several machine learning tasks, where the goal is to make predictions and discover patterns. However, learning an optimal graph from data is still a challenging task. Weighted K-nearest neighbor and ϵ-neighborhood methods are among the most common graph construction methods, due to their computational simplicity but the choice of parameters such as K and ϵ associated with these methods is often ad hoc and lacks a clear interpretation. Read more
Published in US Patent Office, 2019
Methods and systems for training an inspection-related algorithm are provided. One system includes one or more computer subsystems configured for performing an initial training of an inspection-related algorithm with a labeled set of defects thereby generating an initial version of the inspection-related algorithm and applying the initial version of the inspection-related algorithm to an unlabeled set of defects. Read more
Published in IEEE Recent Advances in Intelligent Computational Systems, 2011
A methodology based on median filters for the removal of Salt and Pepper noise by its detection followed by filtering in both binary and gray level images has been proposed in this paper. Read more