BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Department of Electrical & Computer Engineering - ECPv6.16.2//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://ece.northeastern.edu
X-WR-CALDESC:Events for Department of Electrical & Computer Engineering
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20200308T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20201101T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20210314T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20211107T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20220313T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20221106T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20211006T110000
DTEND;TZID=America/New_York:20211006T120000
DTSTAMP:20260522T030900
CREATED:20211004T224056Z
LAST-MODIFIED:20211004T224056Z
UID:5222-1633518000-1633521600@ece.northeastern.edu
SUMMARY:ECE PhD Proposal Review: Bin Sun
DESCRIPTION:PhD Proposal Review: Lightweight Neural Networks via Factorization \nBin Sun \nLocation: Zoom Link \nAbstract: Deep learning has become popular in recent years primarily due to powerful computing devices such as GPUs. However\, many applications such as face alignment\, image classification\, and gesture recognition need to be deployed to multimedia devices\, smartphones\, or embedded systems with limited resources. Thus\, there is an urgent need for high-performance but memory-efficient deep learning models. For this\, we design several lightweight deep learning models for different tasks with factorization strategies. \nSpecifically\, we constructed a lightweight face alignment model by proposing a factorization-based deep convolution module named Depthwise Separable Block (DSB) and a light but practical module based on the spatial configuration of the faces. Experiments on four popular datasets verify that Block Mobilenet has better overall performance with less than 1MB storage size. Besides the face analysis application\, we also explored a general\, lightweight deep learning module for image classification with low-rank pointwise residual (LRPR) convolution\, called LRPRNet. Essentially\, LRPR aims at using a low-rank approximation to factorize the pointwise convolution while keeping depthwise convolutions as the residual module to rectify the LRPR module. Moreover\, our LRPR is quite general and can be directly applied to many existing network architectures.\nDue to the success of the factorization strategy on image-based data\, we extended factorization on time sequence data for Sign Language Recognition (SLR). We achieved the first rank in the challenge of SLR with the help of our proposed novel Separable Spatial-Temporal Convolution Network (SSTCN)\, which divides a 3D convolution on joint features into several stages \, which help the SSTCN achieve higher accuracy with fewer parameters.
URL:https://ece.northeastern.edu/event/ece-phd-proposal-review-bin-sun/
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20211006T170000
DTEND;TZID=America/New_York:20211006T200000
DTSTAMP:20260522T030900
CREATED:20210929T180818Z
LAST-MODIFIED:20210929T181335Z
UID:5191-1633539600-1633550400@ece.northeastern.edu
SUMMARY:Showcase of Opportunities for Undergraduate Research and Creative Endeavor (SOURCE)
DESCRIPTION:Calling all Huskies! Learn more about what cutting-edge research and creative endeavor look like at Northeastern. This is your chance to talk one-on-one with faculty from across the colleges about their research – and how you can get involved in projects during your time at Northeastern. Not everyone will have open positions right now but you’ll get a chance to see the range of work that’s happening and begin to make connections that you can build for the rest of your time at Northeastern. \nBefore you attend\, here’s some advice to consider. \n\nTake a look and see who’ll be there. We have an online database of attendees. Go through it and learn more about the project areas and visit the researcher/creative practitioner web pages. This will help prepare you for a conversation and help you ask any questions you might have.\nGet ready for a conversation from your end. Think about goals you have \, as well as your current interests and skills and those that you want to develop. How does what you have read about the various projects align with what you know about yourself and your interests? Take a minute to practice a simple declarative sentence\, “My name is ____________. I study ____________. I think that this part of your work ____________ is interesting because of this intellectual reason/moral imperative/grand impact ____________.  I’d love to learn more about it because of this previous experience ____________ and these skills ____________ and my long-term interest in ____________.  How I can get involved?” You might not know how to fill in all of the blanks right now (that’s why you’re in school) but see how close you can get.  When you know who you are\, what you value\, and how you can contribute — and get some practice saying it out loud– being confident becomes easier.\nRemember\, not every faculty member will have open positions now — but a good impression lasts a long time. You can’t go wrong with being polite and courteous.   Address faculty members as Professor until told otherwise (better to err on the side of formality).\nKeep in mind your time! If you want to be involved in research or creative practice\, a good thing to keep in mind is that faculty members will commit a lot of time to training and mentoring their undergraduates. They’re investing time\, energy\, and expertise in their mentees and want to know that you will make time for the projects\, show up consistently\, and ideally be with them for longer than a semester if possible. The learning curve of most projects is steep and it takes some time to get to the meatiest parts of the work. Be honest with yourself about the commitment you can make\, be frank with your faculty mentors\, and stick to your word. Communication and honesty in relationships\, including the mentoring relationship\, is key.\n\nSOURCE is a collaboration between Bouvé College of Health Sciences; College of Arts\, Media and Design; College of Engineering; College of Science; College of Social Sciences and Humanities; D’Amore-McKim School of Business; and Khoury College of Computer Science. It is coordinated by Undergraduate Research and Fellowships on behalf of the Office of the Chancellor.
URL:https://ece.northeastern.edu/event/showcase-of-opportunities-for-undergraduate-research-and-creative-endeavor/
LOCATION:Curry Student Center\, 360 Huntington Ave.\, Boston\, MA\, 02115\, United States
GEO:42.3394629;-71.0885286
X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=Curry Student Center 360 Huntington Ave. Boston MA 02115 United States;X-APPLE-RADIUS=500;X-TITLE=360 Huntington Ave.:geo:-71.0885286,42.3394629
END:VEVENT
END:VCALENDAR