Yann LeCun Deep Learning Interview

Yann LeCun Deep Learning Interview

Yann LeCun Deep Learning Interview

Yann LeCun Deep Learning : NYU Courant Professor of Machine Learning Yann LeCun talks with Rebellion Research on his perspective on the future of Artificial Intelligence.

Many professors in the academic community will give credit to Yann LeCun for being the Godfather of Deep Learning. Professor LeCun’s work with computer visuals is groundbreaking and revolutionary.

When Professor LeCun was at Bell Labs before becoming Facebook’s Director of Artificial Intelligence, LeCun published a paper on gradient descent that many people also say changed the landscape of Machine Learning thinking when dealing with object recognition in both the academic and corporate setting.

Yann LeCun Deep Learning : Why does Deep Learning work?

Publications

• Feature Learning and Deep Architectures: New Directions for Music Informaticspublication dateDec 2013  publication descriptionJournal of Intelligent Information Systems / SpringerOther authorsSee publication Feature Learning and Deep Architectures: New Directions for Music InformaticsSee publication : First, we critically review the standard approach to music signal analysis and identify three specific deficiencies to current methods: hand-crafted feature design is sub-optimal and unsustainable, the power of shallow architectures is fundamentally limited, and short-time analysis cannot encode musically meaningful structure. Acknowledging breakthroughs in other perceptual AI domains, we offer that deep learning holds the potential to overcome each of these obstacles. Through conceptual arguments for feature learning and deeper processing architectures, we demonstrate how deep processing models are more powerful extensions of current methods, and why now is the time for this paradigm shift. Finally, we conclude with a discussion of current challenges and the potential impact to further motivate an exploration of this promising research area.
• Moving Beyond Feature Design: Deep Architectures and Automatic Feature Learning in Music Informaticspublication dateOct 24, 2012  publication descriptionProc. of the International Society of Music Information Retrieval (ISMIR) 2012Other authorsSee publication Moving Beyond Feature Design: Deep Architectures and Automatic Feature Learning in Music InformaticsSee publication
• Predictive network modeling of the high-resolution dynamic plant transcriptome in response to nitratepublication date2010  publication descriptionGenome BiologyOther authors
• Classification of patterns of EEG synchronization for seizure predictionpublication date2009  publication descriptionClinical NeurophysiologyOther authors
• Comparing SVM and convolutional networks for epileptic seizure prediction from intracranial EEGpublication dateOct 2008  publication descriptionIEEE Workshop on Machine Learning for Signal ProcessingOther authors

Yann has 3 projects:

Projects

• LAGR
• DjVu
• Check Recognition with Deep Learning