NUDeepLearning

[NUDeepLearning @NUDeepLearning]

Learn about the "magic numbers" that can produce more efficient TimeGPT forecasts with CDL's Dr. Raman Khurana: https://t.co/2BJ5oXXFHG
#TimeSeries #AI #Forecasting #DataScience #Innovation #timegpt #Deeplearning #TransferLearning

[NUDeepLearning @NUDeepLearning]

Join us for CDL's Fall Seminar on October 25th, featuring Dr. Peyman Davoudabadi of ANSYS, Inc. Learn more and RSVP here: https://t.co/33PESCWV2D

[NUDeepLearning @NUDeepLearning]

CDL Spring Researcher Spotlight: Erick Mungai. Learn about Erick's work implementing and testing unstructured data processing capabilities for the DELOS project: https://t.co/xVNpl9PyI4 #DeepLearning #Northwestern

[NUDeepLearning @NUDeepLearning]

Join us on April 12th as CDL welcomes Dan Reaume for his seminar "Enabling Smart Innovation at Caterpillar with Analytics"! Learn more and RSVP here: https://t.co/33PESCWV2D

[NUDeepLearning @NUDeepLearning]

CDL is spotlighting student researcher Joseph Holtzman after a highly productive quarter improving the DELOS drift stress testing module. Read more about his work here: https://t.co/fKHfcwXqXt
#deeplearning #cdl #northwestern

[NUDeepLearning @NUDeepLearning]

Join Diego Klabjan @dklabjan and Yegna Jambunath at ODSC West for their talk "MLOps for Deep Learning"! Register here: https://t.co/t4iQ8eiNet #DeepLearning

[NUDeepLearning @NUDeepLearning]

and impressive overall knowledge of DELOS. Thank you for your continuing work on the project, and we look forward to watching your career grow going forward!

[NUDeepLearning @NUDeepLearning]

Hall of Fame-DELOS: Joseph Holtzman

Joseph has been a major contributor to the DELOS project since joining the team in June. In the past two months, he has implemented unit testing for DELOS’ ClientAPI and Drift components as well as a Mongo DB helm chart. (1/4)

[NUDeepLearning @NUDeepLearning]

and implement elegant solutions, Joseph has contributed significantly to the overall success of DELOS as a software package. Strong quarterly internal reports, as well as key assistance in client implementation have demonstrated his strong communication skills (3/4)

[NUDeepLearning @NUDeepLearning]

The talk abstract and more information on the Center for Deep Learning are available on our website:https://t.co/33PESCWV2D #MLOps #deeplearning

[NUDeepLearning @NUDeepLearning]

Yegna Jambunath and Professor Diego Klabjan will be presenting their talk "MLOps for Deep Learning" at a pair of conferences this June, and we encourage you to join! The first is MLOps World in Toronto on June 10th: https://t.co/PNj4kcUDPB

[NUDeepLearning @NUDeepLearning]

The first talk has been listed as a Top 8 Recommended Session for MLOps World, so be sure to stop by if you are attending! https://t.co/Dy9oU3PYMs Registration is still open for both conferences.

[NUDeepLearning @NUDeepLearning]

Join us this Thursday, April 14th at 5PM for Plamen Petrov's seminar at CDL! The event will be held in Ford 2350 and online, and is open to all interested Northwestern students and faculty. RSVP here: https://t.co/gf9bmXRRua

[NUDeepLearning @NUDeepLearning]

Join us next Thursday, February 10th at 5PM for Plamen Petrov's seminar at CDL! The event will be held in Ford 2350 and online, and is open to all interested Northwestern students and faculty. RSVP here: https://t.co/8UK6jnMKvj

[NUDeepLearning @NUDeepLearning]

The Center for Deep Learning has an opening for a Post-Doctoral Researcher in the area of Deep Learning. Please follow the link to learn more about the position and its responsibilities, and share!

https://t.co/SxgcbIwabO

[NUDeepLearning @NUDeepLearning]

Center for Deep Learning releases summer newsletter: read about REFIT's use case analyzing data from the City of Chicago's IoT traffic data along with weather data: https://t.co/tOsNicHuol

[NUDeepLearning @NUDeepLearning]

Read it here: https://t.co/YS8mVbN3dE

[NUDeepLearning @NUDeepLearning]

Despite incredible accuracy achievements, neural network classifiers inevitably make mistakes. New paper by @dklabjan & Huiyu Wu derives an uncertainty measure based on logit outputs of neural networks that help models detect when more likely to make mistakes.