Eugene John — accepted AI-conference papers

2024

Differentiable Weightless Neural Networks

Alan Tendler Leibel Bacellar, Zachary Susskind, Mauricio Breternitz Jr, Eugene John, Lizy Kurian John, Priscila Machado Vieira Lima +1

ICML 2024poster

We introduce the Differentiable Weightless Neural Network (DWN), a model based on interconnected lookup tables. Training of DWNs is enabled by a novel Extended Finite Difference technique for approximate differentiation of binary values. We propose Learnable Mapping, Learnable Reduction, and Spectra…

Cited by 9 Source ↗PDF ↗code ↗Scholar ↗

2021

Quickest Joint Detection and Classification of Faults in Statistically Periodic Processes

Taposh Banerjee, Smruti Padhy, Ahmad F. Taha, Eugene John

ICASSP 2021accepted

An algorithm is proposed to detect and classify a change in the distribution of a stochastic process that has periodic statistical behavior. The problem is posed in the framework of independent and periodically identically distributed (i.p.i.d.) processes, a recently introduced class of processes to…

Cited by 0 Source ↗Scholar ↗

2020

Sequential Methods for Detecting a Change in the Distribution of an Episodic Process

Taposh Banerjee, Edmond Adib, Ahmad F. Taha, Eugene John

ICASSP 2020accepted

A new class of stochastic processes called episodic processes is introduced to model the statistical regularity of data observed in several applications in cyberphysical systems, neuroscience, and medicine. Algorithms are proposed to detect a change in the distribution of episodic processes. The alg…

Cited by 0 Source ↗Scholar ↗