Samy Bengio : 2012 Plenary Session


Tuesday, April 3, 2012
Location: Fisher Conference Center, Arrillaga Alumni Center

"Large Scale Semantic Extraction Through Embeddings: From Images to Music"
9:15am - 9:45am


Image annotation datasets are becoming larger and larger, with tens of millions of images and tens of thousands of possible annotations.

In the first part of the talk, I'll introduce WSABIE, a strongly performing method that scales to such datasets by simultaneously learning to optimize precision at k of the ranked list of annotations for a given image and learning a low-dimensional joint embedding space for both images and annotations. Our method both outperforms several baseline methods and, in comparison to them, is faster and consumes less memory. We also demonstrate how our method learns an interpretable model, where annotations with alternate spellings or even languages are close in the embedding space. Hence, even when our model does not predict the exact annotation given by a human labeler, it often predicts similar annotations.

In the second part of the talk, I'll show how the same approach, WSABIE, can be extended to the multi-task case, where one learns simultaneously to embed in the same space various music related information such as artist names, music genres, and audio tracks in order to optimize different but related costs.


Samy Bengio has received his PhD in Computer Science from Unveristy of Montreal in 1993. He is a Research Scientists at Google since 2007. Before that, he was senior researcher in statistical machine learning at IDIAP Research Institute since 1999, where he supervised PhD students and postdoctoral fellows. His research interests span many areas of machine learning such as support vector machines, time series prediction, mixture models, large-scale problems, speech recognition, multi channel and asynchronous sequence processing, multi-modal (face and voice) person authentication, brain computer interfaces, and document retrieval. He is on the editorial boards of the Journal of Machine Learning Research and the Machine Learning Journal, has been general chair of the Workshops on Machine Learning for Multimodal Interactions (MLMI'2004, 2005 and 2006), programme chair of the IEEE Workshop on Neural Networks for Signal Processing (NNSP'2002), and on the programme committee of several international conferences such as NIPS, ICML, ECML and IJCAI.