Faculty of Engineering
Bar Ilan University, Ramat-Gan, Israel 52900
jacob.goldberger at biu.ac.il
machine learning and deep learning algorithms
|My research deals with developing and analyzing efficient and effective machine learning and deep learning algorithms, and applying these algorithms to a large variety of applications such as computer vision, signal processing, medical image processing, speech processing, and natural language processing.|
Recent Deep Learning Publications:
- Information-theory interpretation of the skip-gram negative-sampling objective function., Oren Melamud and Jacob Goldberger, Annual Meeting of the Association for Computational Linguistics (ACL), 2017.
- Training deep neural-networks using a noise adaptation layer. Jacob Goldberger and Ehud Ben-Reuven, Int. Conference on Learning Representations (ICLR) , 2017. code
- Training deep neural-networks based on unreliable labels, Alan Joseph Bekker and Jacob Goldberger, IEEE Int. Conf. on Acoustic, Speech and Signal Processing (ICASSP), 2016.
- Context2vec: learning generic context embedding with bidirectional LSTM. Oren Melamud, Jacob Goldberger and Ido Dagan, Conference on Computational Natural Language Learning (CoNLL) , 2016.
- A multi-view deep learning architecture for classification of breast microcalcifications. Alan Joseph Bekker, Hayit Greenspan and Jacob Goldberger, IEEE International Symposium on Biomedical Imaging (ISBI), 2016.
- A semisupervised approach for language identification based on ladder networks. Ehud Ben-Reuven and Jacob Goldberger, Odyssey Speaker and Language Recognition Workshop, 2016.
- A pre-training approach for deep neural network with application to speech enhancement. Shlomo E. Chazan, Sharon Gannot and Jacob Goldberger, Int. Workshop on Acoustic Signal Enhancement (IWAENC), 2016. Best student paper award
- Intra-cluster training strategy for deep learning with applications to language identification. Alan Jospeh Bekker, Irit Opher, Itsik Lapidot and Jacob Goldberger. IEEE International Workshop on Machine Learning for Signal Processing (MLSP), 2016.