This was an invited talk by Yann LeCun at CVPR 2015. The video is here and the slides are here: What's Wrong with Deep Learning? (h/t Andrei and Gabriel)
I note that what is missing in deep Learning revolves around unsupervised learning and is the subject of most interrogations in compressive sensing and advanced matrix factorizations as per the issue of encoding, decoding and regularizers.
Liked this entry ? subscribe to Nuit Blanche's feed, there's more where that came from. You can also subscribe to Nuit Blanche by Email, explore the Big Picture in Compressive Sensing or the Matrix Factorization Jungle and join the conversations on compressive sensing, advanced matrix factorization and calibration issues on Linkedin.