Search Results for author: Saikat Chatterjee

Found 32 papers, 7 papers with code

Use of Deterministic Transforms to Design Weight Matrices of a Neural Network

no code implementations6 Oct 2021 Pol Grau Jurado, Xinyue Liang, Alireza M. Javid, Saikat Chatterjee

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).

Object Classification

Normalizing Flow based Hidden Markov Models for Classification of Speech Phones with Explainability

1 code implementation1 Jul 2021 Anubhab Ghosh, Antoine Honoré, Dong Liu, Gustav Eje Henter, Saikat Chatterjee

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.

Classification

Chern-Weil theory for principal bundles over Lie groupoids and differentiable stacks

no code implementations15 Dec 2020 Indranil Biswas, Saikat Chatterjee, Praphulla Koushik, Frank Neumann

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

Atiyah sequences and connections on principal bundles over differentiable stacks

no code implementations15 Dec 2020 Indranil Biswas, Saikat Chatterjee, Praphulla Koushik, Frank Neumann

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

Pushforwards and Gauge Transformations for Categorical Connections

no code implementations15 Dec 2020 Saikat Chatterjee, Amitabha Lahiri, Ambar N. Sengupta

We construct and study pushforwards of categorical connections on categorical principal bundles.

Differential Geometry Mathematical Physics Mathematical Physics Primary: 18D05, Secondary: 20C99

Statistical model-based evaluation of neural networks

1 code implementation18 Nov 2020 Sandipan Das, Prakash B. Gohain, Alireza M. Javid, Yonina C. Eldar, Saikat Chatterjee

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

1 code implementation22 Oct 2020 Alireza M. Javid, Sandipan Das, Mikael Skoglund, Saikat Chatterjee

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

no code implementations29 Sep 2020 Xinyue Liang, Alireza M. Javid, Mikael Skoglund, Saikat Chatterjee

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

no code implementations7 May 2020 Alireza M. Javid, Xinyue Liang, Arun Venkitaraman, Saikat Chatterjee

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.

Time Series

Asynchronous Decentralized Learning of a Neural Network

no code implementations10 Apr 2020 Xinyue Liang, Alireza M. Javid, Mikael Skoglund, Saikat Chatterjee

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

no code implementations29 Mar 2020 Alireza M. Javid, Arun Venkitaraman, Mikael Skoglund, Saikat Chatterjee

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

no code implementations26 Nov 2019 Arun Venkitaraman, Saikat Chatterjee, Bo Wahlberg

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

no code implementations30 Oct 2019 Antoine Honore, Dong Liu, David Forsberg, Karen Coste, Eric Herlenius, Saikat Chatterjee, Mikael Skoglund

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

1 code implementation13 Oct 2019 Dong Liu, Antoine Honoré, Saikat Chatterjee, Lars K. Rasmussen

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

no code implementations23 Aug 2019 Dong Liu, Nima N. Moghadam, Lars K. Rasmussen, Jinliang Huang, Saikat Chatterjee

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.

SSFN -- Self Size-estimating Feed-forward Network with Low Complexity, Limited Need for Human Intervention, and Consistent Behaviour across Trials

no code implementations17 May 2019 Saikat Chatterjee, Alireza M. Javid, Mostafa Sadeghi, Shumpei Kikuta, Dong Liu, Partha P. Mitra, Mikael Skoglund

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.

Image Classification

Entropy-regularized Optimal Transport Generative Models

no code implementations16 Nov 2018 Dong Liu, Minh Thành Vu, Saikat Chatterjee, Lars K. Rasmussen

We investigate the use of entropy-regularized optimal transport (EOT) cost in developing generative models to learn implicit distributions.

Image Generation

Kernel Regression for Graph Signal Prediction in Presence of Sparse Noise

no code implementations6 Nov 2018 Arun Venkitaraman, Pascal Frossard, Saikat Chatterjee

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

no code implementations31 Mar 2018 Ahmed Zaki, Saikat Chatterjee, Partha P. Mitra, Lars K. Rasmussen

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.

Sparse Learning

Gaussian Processes Over Graphs

no code implementations15 Mar 2018 Arun Venkitaraman, Saikat Chatterjee, Peter Händel

We propose Gaussian processes for signals over graphs (GPG) using the apriori knowledge that the target vectors lie over a graph.

Gaussian Processes

Extreme Learning Machine for Graph Signal Processing

no code implementations12 Mar 2018 Arun Venkitaraman, Saikat Chatterjee, Peter Händel

In this article, we improve extreme learning machines for regression tasks using a graph signal processing based regularization.

R3Net: Random Weights, Rectifier Linear Units and Robustness for Artificial Neural Network

no code implementations12 Mar 2018 Arun Venkitaraman, Alireza M. Javid, Saikat Chatterjee

We consider a neural network architecture with randomized features, a sign-splitter, followed by rectified linear units (ReLU).

Multi-kernel Regression For Graph Signal Processing

no code implementations12 Mar 2018 Arun Venkitaraman, Saikat Chatterjee, Peter Händel

We develop a multi-kernel based regression method for graph signal processing where the target signal is assumed to be smooth over a graph.

Large Neural Network Based Detection of Apnea, Bradycardia and Desaturation Events

no code implementations17 Nov 2017 Antoine Honoré, Veronica Siljehav, Saikat Chatterjee, Eric Herlenius

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.

General Classification

Progressive Learning for Systematic Design of Large Neural Networks

1 code implementation23 Oct 2017 Saikat Chatterjee, Alireza M. Javid, Mostafa Sadeghi, Partha P. Mitra, Mikael Skoglund

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

no code implementations22 Sep 2017 Ahmed Zaki, Partha P. Mitra, Lars K. Rasmussen, Saikat Chatterjee

The algorithm is iterative and exchanges intermediate estimates of a sparse signal over a network.

A Connectedness Constraint for Learning Sparse Graphs

1 code implementation29 Aug 2017 Martin Sundin, Arun Venkitaraman, Magnus Jansson, Saikat Chatterjee

We especially show how the constraint relates to the distributed consensus problem and graph Laplacian learning.

Bayesian Learning for Low-Rank matrix reconstruction

no code implementations23 Jan 2015 Martin Sundin, Cristian R. Rojas, Magnus Jansson, Saikat Chatterjee

We develop latent variable models for Bayesian learning based low-rank matrix completion and reconstruction from linear measurements.

Latent Variable Models Low-Rank Matrix Completion

Combined modeling of sparse and dense noise for improvement of Relevance Vector Machine

no code implementations12 Jan 2015 Martin Sundin, Saikat Chatterjee, Magnus Jansson

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.

Image Denoising

Cannot find the paper you are looking for? You can Submit a new open access paper.