Search Results for author:
Found 24 papers, 1 papers with code
Scalable Twin Neural Networks for Classification of Unbalanced Data
In this paper, we discuss a Twin Neural Network (Twin NN) architecture for learning from large unbalanced datasets.
Learning Neural Network Classifiers with Low Model Complexity
Our proposed approach yields benefits across a wide range of architectures, in comparison to and in conjunction with methods such as Dropout and Batch Normalization, and our results strongly suggest that deep learning techniques can benefit from model complexity control methods such as the LCNN learning rule.
Examining Representational Similarity in ConvNets and the Primate Visual Cortex
We compare several ConvNets with different depth and regularization techniques with multi-unit macaque IT cortex recordings and assess the impact of the same on representational similarity with the primate visual cortex.
Feature Selection for classification of hyperspectral data by minimizing a tight bound on the VC dimension
Hyperspectral data consists of large number of features which require sophisticated analysis to be extracted.
Benchmarking NLopt and state-of-art algorithms for Continuous Global Optimization via Hybrid IACO$_\mathbb{R}$
This paper presents a comparative analysis of the performance of the Incremental Ant Colony algorithm for continuous optimization ($IACO_\mathbb{R}$), with different algorithms provided in the NLopt library.
A Neurodynamical System for finding a Minimal VC Dimension Classifier
The recently proposed Minimal Complexity Machine (MCM) finds a hyperplane classifier by minimizing an exact bound on the Vapnik-Chervonenkis (VC) dimension.
Learning a Fuzzy Hyperplane Fat Margin Classifier with Minimum VC dimension
The Vapnik-Chervonenkis (VC) dimension measures the complexity of a learning machine, and a low VC dimension leads to good generalization.
Feature Selection through Minimization of the VC dimension
For a linear hyperplane classifier in the input space, the VC dimension is upper bounded by the number of features; hence, a linear classifier with a small VC dimension is parsimonious in the set of features it employs.
Learning a hyperplane regressor by minimizing an exact bound on the VC dimension
The capacity of a learning machine is measured by its Vapnik-Chervonenkis dimension, and learning machines with a low VC dimension generalize better.
Learning a hyperplane classifier by minimizing an exact bound on the VC dimension
The VC dimension measures the capacity of a learning machine, and a low VC dimension leads to good generalization.
Radius-margin bounds for deep neural networks
Explaining the unreasonable effectiveness of deep learning has eluded researchers around the globe.
Effect of Various Regularizers on Model Complexities of Neural Networks in Presence of Input Noise
We show that $L_2$ regularization leads to a simpler hypothesis class and better generalization followed by DARC1 regularizer, both for shallow as well as deeper architectures.
Smaller Models, Better Generalization
Reducing network complexity has been a major research focus in recent years with the advent of mobile technology.
Guided Random Forest and its application to data approximation
We present a new way of constructing an ensemble classifier, named the Guided Random Forest (GRAF) in the sequel.
Enhash: A Fast Streaming Algorithm For Concept Drift Detection
We propose Enhash, a fast ensemble learner that detects \textit{concept drift} in a data stream.
Complexity Controlled Generative Adversarial Networks
One of the issues faced in training Generative Adversarial Nets (GANs) and their variants is the problem of mode collapse, wherein the training stability in terms of the generative loss increases as more training data is used.
Twin Augmented Architectures for Robust Classification of COVID-19 Chest X-Ray Images
We show that popular choices of dataset selection suffer from data homogeneity, leading to misleading results.
HybMT: Hybrid Meta-Predictor based ML Algorithm for Fast Test Vector Generation
As compared to a popular, state-of-the-art commercial ATPG tool, HybMT shows an overall reduction of 56. 6% in the CPU time without compromising on the fault coverage for the EPFL benchmark circuits.
Predicting Oxide Glass Properties with Low Complexity Neural Network and Physical and Chemical Descriptors
In addition, we combine the LCNN with physical and chemical descriptors that allow the development of universal models that can provide predictions for components beyond the training set.
Cementron: Machine Learning the Constituent Phases in Cement Clinker from Optical Images
Specifically, we finetune the image detection and segmentation model Detectron-2 on the cement microstructure to develop a model for detecting the cement phases, namely, Cementron.
Graph Neural Stochastic Differential Equations for Learning Brownian Dynamics
Here, we propose a framework, namely Brownian graph neural networks (BROGNET), combining stochastic differential equations (SDEs) and GNNs to learn Brownian dynamics directly from the trajectory.
Discovering Symbolic Laws Directly from Trajectories with Hamiltonian Graph Neural Networks
Here, we present a Hamiltonian graph neural network (HGNN), a physics-enforced GNN that learns the dynamics of systems directly from their trajectory.
MaScQA: A Question Answering Dataset for Investigating Materials Science Knowledge of Large Language Models
Further, we evaluate the performance of GPT-3. 5 and GPT-4 models on solving these questions via zero-shot and chain of thought prompting.
No prejudice! Fair Federated Graph Neural Networks for Personalized Recommendation
However, integrating these graph models into the Federated Learning (FL) paradigm with fairness constraints poses formidable challenges as this requires access to the entire interaction graph and sensitive user information (such as gender, age, etc.)
