Mainak Ghosh, M.Sc.

Doktorand und wissenschaftlicher Mitarbeiter

Innovation and Entrepreneurship Research

+49 89 24246-574
mainak.ghosh(at)ip.mpg.de

Persönliche Website:

https://ghoshmainak.github.io

Arbeitsbereiche:

Maschinelles Lernen, Natürliche Spracherkennung und -verarbeitung, Sentiment-Analyse

Wissenschaftlicher Werdegang

Seit 03/2020
Wissenschaftlicher Mitarbeiter und Doktorand, Max-Planck-Institut für Innovation und Wettbewerb (Innovation and Entrepreneurship Research)

10/2017 - 11/2019
Master of Science (M.Sc.) im Studiengang “Data Engineering and Analytics”, Technische Universität München (TUM); Titel der Masterarbeit: “Multilingual Opinion Mining on Social Media Comments Using Unsupervised Neural Clustering Methods”

11/2017 - 02/2018
Studentischer Mitarbeiter, Max-Planck-Institut für Sozialrecht und Sozialpolitik, München

05/2013 - 07/2013
Forschungspraktikum, Indian Statistical Institute, Kalkutta, Indien

06/2012 - 07/2012
Praktikum, Globsyn Business School, Kalkutta, Indien

2010 - 2014
Bachelor of Engineering (B.E.) im Studiengang “Computer Science & Technology”, Indian Institute of Engineering Science & Technology, Shibpur, Indien

Beruflicher Werdegang

03/2018 - 03/2020
Werkstudent, IDS GmbH – Analysis and Reporting Services (IDS), München

08/2014 - 09/2017
Softwareingenieur, Acclaris Business Solutions Pvt Ltd, Kalkutta, Indien

Wissenschaftliche Preise und Ehrungen

2013
Zertifikat CCS (Cognizant Certified Student), IT Foundation Skills

2009
Auszeichnung, Mathematischer Kompetenztest, Association for Improvement of Mathematics Teaching (AIMT), Kalkutta, Indien

2008
Zertifikat für besondere Leistungen in Physikwissenschaften und Mechanik

Publikationen

Andere Veröffentlichungen, Presseartikel, Interviews

Hagerer, Gerhard; Moeed, Abdul; Dugar, Sumit; Gupta, Sarthak; Ghosh, Mainak; Danner, Hannah; Mitevski, Oliver; Nawroth, Andreas; Groh, Georg (2020). An Evaluation of Progressive Neural Networks for Transfer Learning in Natural Language Processing, in: Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020), Marseille, 1376-1381.

  • A major challenge in modern neural networks is the utilization of previous knowledge for new tasks in an effective manner, otherwise known as transfer learning. Fine-tuning, the most widely used method for achieving this, suffers from catastrophic forgetting. The problem is often exacerbated in natural language processing (NLP). In this work, we assess progressive neural networks (PNNs) as an alternative to fine-tuning. The evaluation is based on common NLP tasks such as sequence labeling and text classification. By gauging PNNs across a range of architectures, datasets, and tasks, we observe improvements over the baselines throughout all experiments.
  • Conference Paper
  • Conference Volume
  • Event: 12th Language Resources and Evaluation Conference, Marseille, 2020-05-11

Vorträge

10.09.2020
Knowledge Mining, Digitalization, Machine Learning
Forschungsseminar
Ort: online (München)