College of Engineering Home

Mechanical Engineering (MNE) Seminar DATE: Friday, 3/31/23 TIME: 2:00 p.m. - 3:00 p.m. LOCATION: Science & Engineering Building, Room 115 (SENG-115) and Zoom: https://umassd.zoom.us/j/91640406955?pwd=eklBZWVDOXVDa2VwUFMra1kwNWhjdz09 (Passcode: 500) SPEAKERS: -Adam Fiore, MNE MS student, advised by Dr. Sankha Bhowmick -Joshua W. Letizia, MNE MS student, advised by Dr. Vijay Chalivendra -Ersen'S Joseph, MNE MS student, advised by Dr. Amit Tandon and Dr. Tom Farrar All are welcome! Students taking MNE-500 are REQUIRED to attend! All other MNE BS and MS students are encouraged to attend. EAS students are also encouraged to attend. For more information, please contact Dr. Hangjian Ling, MNE Seminar Coordinator (hling1@umassd.edu).

Science and Engineering Building

Fall Registration Begins

UMass Dartmouth

Today is the last day to withdraw from a class.

UMass Dartmouth

Topic: Implementation of Analog Electronic Hardware for Training Neural Networks Location: LC Conference Room, Science & Engineering Building (SENG), Room 213A Zoom Conference Link: https://umassd.zoom.us/j/95661551262 Meeting ID: 956 6155 1262 Passcode: 645260 Abstract: Most current training methods for Artificial Neural Networks (ANNs) run as software emulations, as opposed to an on-chip training approach. Although it is convenient to have training done through software as opposed to on a hardware build, there are several drawbacks to this approach. The primary cost of this convenience is the amount of time it takes to train an ANN. Emulated training methods are slower than real-time on-chip training, with the amount of training time increasing with the complexity of the ANN. When training in real-time each neuron can be trained at once, taking advantage of the inherent parallelism of ANNs, and decreasing training times markedly. This thesis includes a discussion of an analog hardware implementation for training neural networks, and an evaluation and design explanation of an ANN which has been built on physical hardware as a proof-of-concept. The ANN is designed to perform pattern recognition on handwritten digits from zero to nine and uses the MNIST data set as a source for the figures used in training. The output-layer section of this ANN, where all of the training is completed, is built entirely in analog hardware in order to prove the potential advantages over training in software. Advisor(s): Dr. David P. Rancour, Associate Professor, Department of Electrical & Computer Engineering, UMASS Dartmouth Committee Members: Dr. Dayalan P. Kasilingam, Professor, Department of Electrical & Computer Engineering, UMASS Dartmouth Dr. Paul J. Fortier, Professor Emeritus, Department of Electrical & Computer Engineering, UMASS Dartmouth NOTE: All ECE Graduate Students are ENCOURAGED to attend. All interested parties are invited to attend. Open to the public. *For further information, please contact Dr. David Rancour via email at drancour@umassd.edu

See description for location

Patriots' Day holiday, no classes today.

UMass Dartmouth

Follow Monday's schedule.

UMass Dartmouth