Karl Trela

Data Scientist, Economist, Design Thinker @Fraunhofer IMW in Leipzig, Germany

[Karl Trela @KarlTrela]

How to find industry partners for public research? In our new #IEEE paper @yuricampbll, Friedrich Dornbusch, Anna Pohle and I present the classification approach behind our tool Corporate-Match, which helps 70 @Fraunhofer institutes with that. Paper: https://t.co/3bfx0YFF89 1/5

[Data Science for Innovation @inno_data]

📢We are excited to announce our paper "
Deep Learning-based Computational Job Market Analysis: A Survey on Skill Extraction and Classification from Job Postings" has been accepted to #EACL2024 at the @nlp4hr workshop.

In cooperation with @NLPnorth and @MaiNLPlab.

[Karl Trela @KarlTrela]

@innogeo @EU2020DE Das Ding heißt Möbius-Schleife. Wieder was gelernt. https://t.co/3ZxLj8d2fW

[BMFTR @bmftr_bund]

Die Möbius-Schleife wird uns durch die 🇩🇪 EU-Ratspräsidentschaft #EU2020DE begleiten. Mit ihren besonderen Eigenschaften (sie hat nur eine Seite!) steht sie für die Verbundenheit Europas. Der Wissenschaftler A.F. Möbius beschrieb die Figur als Erster 👉 https://t.co/068t5vrHzT

[Karl Trela @KarlTrela]

What a great result of one summer seminar with students: an entire book. Wish my seminars had been that interesting and productive back then.

[Christoph Molnar 🦋 christophmolnar.bsky.social @ChristophMolnar]

What are some limitations of interpretable machine learning methods?

This summer, our students worked on this question. We compiled the results in a free online book, which we release today. 🎉🎉🎉

Find out more:
https://t.co/hrh2UhGaxN

[Karl Trela @KarlTrela]

I think every Data Scientist has noticed at some point how important and sometimes difficult it is to make your #MachineLearning model interpetable. This looks like an awesome resource with state of the art ways to do it. Will surely check it out. Thanks @ChristophMolnar!

[Christoph Molnar 🦋 christophmolnar.bsky.social @ChristophMolnar]

2 years, 250 pages, 1,219 commits, and 78,480 words:

I am very proud to say that today I published the 1st edition of "Interpretable Machine Learning". 🎉🎉🎉

Web: https://t.co/s4tyZz3f3B
Leanpub: https://t.co/OAIEB1YNzR

[Karl Trela @KarlTrela]

We actually use a variant of this classification approach for our Corporate-Match prototype and our colleagues at @Fraunhofer are quite satisfied with the results. We are still working on improvements and would love to apply it to different organizations in future. 5/5

[Karl Trela @KarlTrela]

How to find industry partners for public research? In our new #IEEE paper @yuricampbll, Friedrich Dornbusch, Anna Pohle and I present the classification approach behind our tool Corporate-Match, which helps 70 @Fraunhofer institutes with that. Paper: https://t.co/3bfx0YFF89 1/5

[Karl Trela @KarlTrela]

Turns out the combination of econometric data, geographic company-institute distance and WZ-industry-codes (German equivalent to NACE) performs the best. Texts which describe the industry branches instead of codes perform slightly worse on average, but with less variance. 4/5

[Karl Trela @KarlTrela]

I really enjoyed discussing our poster at #mlprague together with @algorithm87, on how we try find the right industry partners for our research institutes @Fraunhofer using #MachineLearning methods like text-classification and hybrid recommender systems. Thanks for dropping by!

[Karl Trela @KarlTrela]

Interesting future challenge for machine learning put forward by MITs Tomaso Poggio: " to learn like children"...with just a few labeled observations, possibly wit a lot of unlabeled data. Children do not need a million of pictures to learn how a car looks like. #mlprague

[Karl Trela @KarlTrela]

Wow, what a way to start a conference with playing this organ! #mlprague

[MLPrague @MLPrague]

#mlprague Welcome Speech starts in 10 minutes with a BIG suprise. Go take your seat now!