Jamal Lottier Molin

Jamal Lottier Molin

Auto-generated profile, based on publicly available information

Jamal Lottier Molin

Johns Hopkins University

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
12 August 2021 in IEEE Transactions on Biomedical Circuits and Systems
Verified
Journal Article
Closed access
JMJamal Lottier Molin
Jamal Lottier Molin
CTChetan Singh Thakur
Chetan Singh Thakur
ENErnst Niebur
Ernst Niebur
RERalph Etienne-Cummings
Ralph Etienne-Cummings
Computing and attending to salient regions of a visual scene is an innate and necessary preprocessing step for both biological and engineered systems performing high-level visual tasks including object detection, tracking, and classification. Computational bandwidth and speed are improved by preferentially devoting computational resources to salient regions of the visual field. The human brain computes saliency effortlessly, but modeling this task in engineered systems is challenging. We first present a neuromorphic dynamic saliency model, which is bottom-up, feed-forward, and based on the notion of proto-objects with neurophysiological spatio-temporal features requiring no training. Our neuromorphic model outperforms state-of-the-art dynamic visual saliency models in predicting human eye fixations (i.e., ground truth saliency). Secondly, we present a hybrid FPGA implementation of the model for real-time applications, capable of processing $112\times 84$ resolution frames at 18.71 Hz running at a 100 MHz clock rate — a $23.77\times$ speedup from the software implementation. Additionally, our fixed-point model of the FPGA implementation yields comparable results to the software implementation.

1 March 2017
Verified
Conference Paper
Closed access
CTChetan Singh Thakur
Chetan Singh Thakur
JMJamal Molin
Jamal Molin
RERalph Etienne-Cummings
Ralph Etienne-Cummings
ASAndre van Schaik
Andre van Schaik
We present a stochastic Bayesian neuron (SBN) that codes for a binary hidden variable and the temporal dynamics of which can be explained as a Bayesian inference. We show that our SBN combines the maximum likelihood of its synaptic inputs and the prior probability of the hidden variable to infer the presence of the hidden variable. Probabilistic models are computationally complex, which makes them difficult to implement using standard state-of-the-art digital implementation. Here, we employ stochastic logic elements to implement the SBN using minimum hardware resources. The SBN could be used as a basic element to develop a Bayesian processor that works on probability instead of deterministic logic.


24 March 2021
Verified
Conference Paper
Closed access
NZNishant Zachariah
Nishant Zachariah
IDIsidoros Doxas
Isidoros Doxas
JMJamal Molin
Jamal Molin
Matched filtering is used in radar signal processing for optimal detection of signals in highly noisy environments. In this paper, we demonstrate a novel method for matched matched filtering using 1 bit random encoding called PEERS (Parameter Estimation using Random 1bit streams). PEERS demonstrates three novel results. First, PEERS demonstrates robust parameter estimation with recovery errors $(\Vert y-\hat{y}\Vert_{2}^{2})$ that are as much as 50% lower than matched filtering in highly noisy environments. Secondly, we demonstrate that PEERS is resilient to grid jitter (instances in matched filtering where the signal is not contained in the library) with recovery errors that can be lower than matched filtering by as much as 88%. Finally, while recent work in this area has focused on noise reliance post encoding, we demonstrate a novel way of handling noise pre-encoding which gives rise to the superior estimation results described. Given the 1 bit arithmetic leveraged by PEERS, we demonstrate is efficacy on custom neuromorphic hardware where each PEERS operation consumes less than 20fJ/ operation for extremely low power edge computing.

1 May 2017
Verified
Conference Paper
Closed access
JMJamal Lottier Molin
Jamal Lottier Molin
AEAdebayo Eisape
Adebayo Eisape
RERalph Etienne-Cummings
Ralph Etienne-Cummings
Neuromorphic systems mimic the functionality and communication protocol of biological neurons with efforts to design the most size and power efficient computing systems. We demonstrate the capability of an in-house neural array of 4080 Mihalas-Niebur neurons designed in 0.5μm CMOS technology to perform various event-based image processing tasks including warping and filtering.