Search Results for author:
Found 39 papers, 8 papers with code
Data-driven Bayesian State Estimation with Compressed Measurement of Model-free Process using Semi-supervised Learning
While DANSE provides a good predictive performance to model the temporal measurement data as time-series, its unsupervised learning lacks a regularization for state estimation.
Compressed Sensing of Generative Sparse-latent (GSL) Signals
We consider reconstruction of an ambient signal in a compressed sensing (CS) setup where the ambient signal has a neural network based generative model.
DANSE: Data-driven Non-linear State Estimation of Model-free Process in Unsupervised Learning Setup
DANSE provides a closed-form posterior of the state of the model-free process, given linear measurements of the state.
Automated Sentiment and Hate Speech Analysis of Facebook Data by Employing Multilingual Transformer Models
In recent years, there has been a heightened consensus within academia and in the public discourse that Social Media Platforms (SMPs), amplify the spread of hateful and negative sentiment content.
Neural Greedy Pursuit for Feature Selection
NGP is efficient in selecting $N$ features when $N \ll P$, and it provides a notion of feature importance in a descending order following the sequential selection procedure.
Multi-modal curb detection and filtering
We propose a robust curb detection and filtering technique based on the fusion of camera semantics and dense lidar point clouds.
DeepBayes -- an estimator for parameter estimation in stochastic nonlinear dynamical models
Yet, estimating the unknown parameters of stochastic, nonlinear dynamical models remains a challenging problem.
Use of Deterministic Transforms to Design Weight Matrices of a Neural Network
For the existing SSFN, a part of each weight matrix is trained using a layer-wise convex optimization approach (a supervised training), while the other part is chosen as a random matrix instance (an unsupervised training).
Normalizing Flow based Hidden Markov Models for Classification of Speech Phones with Explainability
For a standard speech phone classification setup involving 39 phones (classes) and the TIMIT dataset, we show that the use of standard features called mel-frequency-cepstral-coeffcients (MFCCs), the proposed generative models, and the decision fusion together can achieve $86. 6\%$ accuracy by generative training only.
Robust Classification using Hidden Markov Models and Mixtures of Normalizing Flows
We test the robustness of a maximum-likelihood (ML) based classifier where sequential data as observation is corrupted by noise.
Pushforwards and Gauge Transformations for Categorical Connections
We construct and study pushforwards of categorical connections on categorical principal bundles.
Differential Geometry Mathematical Physics Mathematical Physics Primary: 18D05, Secondary: 20C99
Atiyah sequences and connections on principal bundles over differentiable stacks
We construct and study general connections on Lie groupoids and differentiable stacks as well as on principal bundles over them using Atiyah sequences associated to transversal tangential distributions.
Differential Geometry Category Theory Primary 53C08, Secondary 22A22, 58H05, 53D50
Connections on Lie groupoids and Chern-Weil theory
Let $\mathbb{X}=[X_1\rightrightarrows X_0]$ be a Lie groupoid equipped with a connection, given by a smooth distribution $\mathcal{H} \subset T X_1$ transversal to the fibers of the source map.
Differential Geometry Category Theory Primary 53C08, Secondary 22A22, 58H05, 53D50
Statistical model-based evaluation of neural networks
Using a statistical model-based data generation, we develop an experimental setup for the evaluation of neural networks (NNs).
A ReLU Dense Layer to Improve the Performance of Neural Networks
We use a combination of random weights and rectified linear unit (ReLU) activation function to add a ReLU dense (ReDense) layer to the trained neural network such that it can achieve a lower training loss.
A Low Complexity Decentralized Neural Net with Centralized Equivalence using Layer-wise Learning
We design a low complexity decentralized learning algorithm to train a recently proposed large neural network in distributed processing nodes (workers).
Predictive Analysis of COVID-19 Time-series Data from Johns Hopkins University
We provide a predictive analysis of the spread of COVID-19, also known as SARS-CoV-2, using the dataset made publicly available online by the Johns Hopkins University.
Asynchronous Decentralized Learning of a Neural Network
In this work, we exploit an asynchronous computing framework namely ARock to learn a deep neural network called self-size estimating feedforward neural network (SSFN) in a decentralized scenario.
High-dimensional Neural Feature Design for Layer-wise Reduction of Training Cost
We show that the proposed architecture is norm-preserving and provides an invertible feature vector, and therefore, can be used to reduce the training cost of any other learning method which employs linear projection to estimate the target.
Recursive Prediction of Graph Signals with Incoming Nodes
Kernel and linear regression have been recently explored in the prediction of graph signals as the output, given arbitrary input signals that are agnostic to the graph.
Hidden Markov Models for sepsis detection in preterm infants
We explore the use of traditional and contemporary hidden Markov models (HMMs) for sequential physiological data analysis and sepsis prediction in preterm infants.
Powering Hidden Markov Model by Neural Network based Generative Models
In the proposed GenHMM, each HMM hidden state is associated with a neural network based generative model that has tractability of exact likelihood and provides efficient likelihood computation.
$α$ Belief Propagation as Fully Factorized Approximation
Belief propagation (BP) can do exact inference in loop-free graphs, but its performance could be poor in graphs with loops, and the understanding of its solution is limited.
Neural Network based Explicit Mixture Models and Expectation-maximization based Learning
A single latent variable is used as the common input to all the neural networks.
SSFN -- Self Size-estimating Feed-forward Network with Low Complexity, Limited Need for Human Intervention, and Consistent Behaviour across Trials
We design a self size-estimating feed-forward network (SSFN) using a joint optimization approach for estimation of number of layers, number of nodes and learning of weight matrices.
Entropy-regularized Optimal Transport Generative Models
We investigate the use of entropy-regularized optimal transport (EOT) cost in developing generative models to learn implicit distributions.
Kernel Regression for Graph Signal Prediction in Presence of Sparse Noise
In presence of sparse noise we propose kernel regression for predicting output vectors which are smooth over a given graph.
Locally Convex Sparse Learning over Networks
Our expectation is that local estimates in each node improve fast and converge, resulting in a limited demand for communication of estimates between nodes and reducing the processing time.
Gaussian Processes Over Graphs
We propose Gaussian processes for signals over graphs (GPG) using the apriori knowledge that the target vectors lie over a graph.
Multi-kernel Regression For Graph Signal Processing
We develop a multi-kernel based regression method for graph signal processing where the target signal is assumed to be smooth over a graph.
R3Net: Random Weights, Rectifier Linear Units and Robustness for Artificial Neural Network
We consider a neural network architecture with randomized features, a sign-splitter, followed by rectified linear units (ReLU).
Extreme Learning Machine for Graph Signal Processing
In this article, we improve extreme learning machines for regression tasks using a graph signal processing based regularization.
Large Neural Network Based Detection of Apnea, Bradycardia and Desaturation Events
Even with a limited and unbalanced training data, the large neural network provides a detection performance level that is feasible to use in clinical care.
Progressive Learning for Systematic Design of Large Neural Networks
The developed network is expected to show good generalization power due to appropriate regularization and use of random weights in the layers.
Estimate Exchange over Network is Good for Distributed Hard Thresholding Pursuit
The algorithm is iterative and exchanges intermediate estimates of a sparse signal over a network.
A Connectedness Constraint for Learning Sparse Graphs
We especially show how the constraint relates to the distributed consensus problem and graph Laplacian learning.
Bayesian Learning for Low-Rank matrix reconstruction
We develop latent variable models for Bayesian learning based low-rank matrix completion and reconstruction from linear measurements.
Combined modeling of sparse and dense noise for improvement of Relevance Vector Machine
Through simulations, we show the performance and computation efficiency of the new RVM in several applications: recovery of sparse and block sparse signals, housing price prediction and image denoising.
Relevance Singular Vector Machine for low-rank matrix sensing
In this paper we develop a new Bayesian inference method for low rank matrix reconstruction.
