So happy to have Laurens van der Maaten from Facebook AI Research give the next talk. Laurens is doing amazing work, so come listen!
Abstract:Convolutional networks constitute the core of state-of-the-art approach to a range of problems in computer vision. Typical networks comprise of tens or even hundreds of layers of convolutions using learned filters, which require a lot of computational & memory resources. In this talk, I will present two new convolutional-network architectures that are substantially more efficient than state-of-the-art residual networks (ResNets), whilst maintaining high predictive accuracy. The first architecture, called DenseNet, connects each layer to every other layer in a feed-forward fashion. For each layer, the feature maps of all preceding layers are used as inputs, & its own feature maps are used as inputs into all subsequent layers. Surprisingly, this substantially reduces the number of parameters needed for the network to perform well, & makes learning easier. The second architecture, called multi-scale DenseNets (MSDNets), extends DenseNets to maintain multi-scale image representations, which allows for the training of multiple classifiers at intermediate layers of the network. This allows us to train a single MSDNet that, at prediction time, dynamically decides the size of the network: for "easy" images, only a small part of the network is evaluated, whilst for "difficult" images, we evaluate the full, high-quality network. MSDNets achieve state-of-the-art performances on image-classification benchmarks with much lower computational requirements.
This talk presents joint work with Gao Huang, Danlu Chen, & Kilian Weinberger of Cornell University.
Bio: Laurens van der Maaten isa research scientist at Facebook AI Research in New York. Prior, he worked as an Assistant Professor at Delft University of Technology (The Netherlands) & as a post-doctoral researcher at University of California, San Diego. He received his PhD from Tilburg University in 2009. He is an editorial board member of IEEE Transactions of Pattern Analysis & Machine Intelligence & is serving as an area chair for the NIPS & ICML conferences.Laurens is interested in a variety of topics in machine learning & computer vision. Specific research topics include learning embeddings for visualization & deep learning, time series classification, regularization, object tracking, & cost-sensitive learning.
Here is a link to his publications:https://lvdmaaten.github.io/publications/
He's done wonderful work recently on Visual Question & Answering & visual reasoning (http://cs.stanford.edu/people/jcjohns/clevr/ )and in the past on T-Sne & many other topics. You can find some of his work on Arxiv as well:https://arxiv.org/find/cs/1/au:+Maaten_L/0/1/0/all/0/1