activity
20172022
most citedProgressive Learning for Systematic Design of Large Neural Networks

23 citations · 47 across the 14 of their papers we have counts for

collaborators
Showing cs.LGShow all

16 papers · 1 filter

cs.LG2021

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

Pol Grau Jurado, Xinyue Liang, Alireza M. Javid +1

Self size-estimating feedforward network (SSFN) is a feedforward multilayer network. For the existing SSFN, a part of each weight matrix is trained using a layer-wise convex optimi…

cs.LG20214 cited

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

Anubhab Ghosh, Antoine Honoré, Dong Liu +2

In pursuit of explainability, we develop generative models for sequential data. The proposed models provide state-of-the-art classification results and robust performance for speec…

cs.LG20213 cited

Robust Classification using Hidden Markov Models and Mixtures of Normalizing Flows

Anubhab Ghosh, Antoine Honoré, Dong Liu +2

We test the robustness of a maximum-likelihood (ML) based classifier where sequential data as observation is corrupted by noise. The hypothesis is that a generative model, that com…

cs.LG2020

Statistical model-based evaluation of neural networks

Sandipan Das, Prakash B. Gohain, Alireza M. Javid +2

Using a statistical model-based data generation, we develop an experimental setup for the evaluation of neural networks (NNs). The setup helps to benchmark a set of NNs vis-a-vis m…

cs.LG2020

A ReLU Dense Layer to Improve the Performance of Neural Networks

Alireza M. Javid, Sandipan Das, Mikael Skoglund +1

We propose ReDense as a simple and low complexity way to improve the performance of trained neural networks. We use a combination of random weights and rectified linear unit (ReLU)…

cs.LG20202 cited

A Low Complexity Decentralized Neural Net with Centralized Equivalence using Layer-wise Learning

Xinyue Liang, Alireza M. Javid, Mikael Skoglund +1

We design a low complexity decentralized learning algorithm to train a recently proposed large neural network in distributed processing nodes (workers). We assume the communication…