PhD, CS @VT_CS, AWS AI -- Ex-Yahoo. Likes machine & human learning. -- Opinions : Strictly Personal Retweets != Agreement/Endorsement
Seattle, WA
Joined September 2014
- Tweets84
- Following349
- Followers123
- Likes960
Debanjan Datta retweeted
At the #KDD2022 conference this week, @SanghaniCtrVT director Naren Ramakrishnan (@profnaren) reunited with former Ph.D. students @VT_CS now on their own career paths in academia or the tech industry: Feng Chen, @bijayaAdh, Fang Jin, @devDdata.
Debanjan Datta retweeted
Faculty and Ph.D. students @VT_CS @SanghaniCtrVT were among the organizers and presenters at #KDD2022 this week in Washington, DC. The conference was also a good opportunity to meet up with alums and colleagues from other universities.
Debanjan Datta retweeted
Framing Algorithmic Recourse for Anomaly Detection
deepai.org/publication/frami…
by @devDdata, @niustrategy, and @profnaren
#AnomalyDetection #MachineLearning
Debanjan Datta retweeted
Anomaly detection methods compute an anomaly score A(x), and in research, we measure their effectiveness using AUC for the binary decision "anomaly" vs. "not anomaly". But in applications, we need to choose a threshold tau. How can we set tau without having labeled anomalies? 1/
Debanjan Datta retweeted
ODD Workshop at #KDD2021 starts from 8am Pacific time. There are 6 exciting keynote talks and a panel discussion on fairness in outlier detection.
oddworkshop.github.io/
Debanjan Datta retweeted
With the Fall 2021 semester fast approaching, students @SanghaniCtrVT are finishing up their summer internships. Ph.D. student Debanjan Datta (@devDdata) has been working on time series characterization and classification @awscloud, Seattle, WA. @profnaren @VT_CS
Debanjan Datta retweeted
Useful thread w/ refs to recent happenings. cc @devDdata , @ShengzheXu.
Debanjan Datta retweeted
4. Scrutinizing Shipment Records To Thwart Illegal Timber Trade
@devDdata, Sathappan Muthiah, John Simeone, Amelia Meadows, @profnaren
5. Choosing Effective Projections for Fast and Accurate Anomaly Detection
Chen Almagor, Yedid Hoshen
Debanjan Datta retweeted
Glad to announce our #KDD2021 Workshop on Outlier Detection and Description @odd_workshop. Jointly organized with Bryan Hooi, @leman_akoglu, @souravc83, Xiaodong Jiang, @ManishGuptaMG1
Deadline: May 20, 2021
Details: oddworkshop.github.io
@kdd_news
#Anomaly #DataScience
Debanjan Datta retweeted
Detecting Anomalies Through Contrast in Heterogeneous Data
deepai.org/publication/detec…
by Debanjan Datta et al. including @profnaren
#Autoencoder #AnomalyDetection
Debanjan Datta retweeted
Nice to see you on Twitter John! Yes, this recommendation indeed ties in nicely with @SanghaniCtrVT's current work on anomaly detection in large tabular datasets. cc: @devDdata @tripswithtires. Paper available here: people.cs.vt.edu/naren/paper…
The 1st rec mentioned is to improve SIMP enforcement using predictive analytics & machine learning. It'd be great to expand our @WWFscience /@TRAFFIC_WLTrade/@SanghaniCtrVT timber shipment targeting research to include seafood! More on our research here: ojs.aaai.org//index.php/AAAI…
Debanjan Datta retweeted
Goode, Datta, and Ramakrishnan. "Imputing Data for the Fragile Families Challenge: Identifying Similar Survey Questions with Semi-automated Methods." @devDdata @profnaren @VT_DAC doi.org/10.1177%2F2378023118…
Debanjan Datta retweeted
For this new study, Brian Goode @FralinLifeSci conducted modeling through @VT_DAC and teamed up with DAC director @profnaren and @VT_CS Ph.D. student @devDdata to gather and analyze data. @Princeton @PNASNews
A cohort of 160 research teams used a rich dataset and state-of-the-art #MachineLearning and #AI tools to make predictions about the life outcomes of children.
According to a new @PNASNews study, even the best predictions were wrong. @Princeton @VT_DAC
vtnews.vt.edu/articles/2020/…
Debanjan Datta retweeted
Curious that we spend more time congratulating people who have succeeded than encouraging people who have not.
Debanjan Datta retweeted
Wanting to help solve real world challenges brought @devDdata to @VT_DAC. Working w/@WWF he analyzes thousands of lines of export & import data to detect patterns of suspicious timber records related to possible illegal trade. Student Spotlight: bit.ly/2V6PcnS @VT_CS
Debanjan Datta retweeted
Detecting Suspicious Timber Trades, @VT_DAC research in collaboration with @WWF, has been accepted in the IAAI-2020 conference collocated with #AAAI20. Ph.D. student Debanjan Datta @devDdata @VT_CS will present the paper in NYC in Feb. @Raihan0155 @tripswithtires @profnaren
Debanjan Datta retweeted
Awesome new GoPro footage offers eagle-eye view of London on.mash.to/1AmLshN
Debanjan Datta retweeted
Mozilla Ditches Google for Yahoo as Default Search on Firefox: InternetNews: From the 'Is Google Evil? What Ab... bit.ly/1vsesTh