Home / Topics

Deep Learning

Curated by: Wei Fan


Deep learning attempts to model high-level abstractions in data by using multiple processing layers, with complex structures or otherwise, composed of multiple non-linear transformations. It is part of a broader family of machine learning methods based on learning representations of data. An observation, for example an image, can be represented in many ways such as a vector of intensity values per pixel, or in a more abstract way as a set of edges, regions of particular shape, etc. Some representations are better than others at simplifying the learning task. One of the promises of deep learning is replacing “handcrafting features” with “crafting architectures” by using efficient algorithms for unsupervised or semi-supervised feature learning and hierarchical feature extraction.

A good start of deep learning tutorial can be found at http://deeplearning.stanford.edu/

A resourceful tutorial was given by Hinton, Lecun and Bengio:
http://www.iro.umontreal.ca/~bengioy/talks/DL-Tutorial-NIPS2015.pdf


Related KDD2016 Papers

Title & Authors
Robust and Effective Metric Learning Using Capped Trace Norm
Author(s): Zhouyuan Huo, University of Texas, Arlington; Feiping Nie, University of Texas at Arlington; Heng Huang*, Univ. of Texas at Arlington
Convolutional Neural Networks for Steady Flow Approximation
Author(s): Xiaoxiao Guo*, University of Michigan; Wei Li, Autodesk Research; Francesco Iorio,
Large-Scale Item Categorization in e-Commerce Using Multiple Recurrent Neural Networks
Author(s): Hyuna Pyo, NAVER LABS; Jung-Woo Ha*, NAVER LABS; Jeonghee Kim, NAVER LABS
Predict Risk of Relapse for Patients with Multiple Stages of Treatment of Depression
Author(s): Zhi Nie*, Arizona State University; Pinghua Gong, ; Jieping Ye, University of Michigan at Ann Arbor
Deep Crossing: Web-Scale Modeling without Manually Crafted Combinatorial Features
Author(s): Ying Shan*, Microsoft Corporation; Thomas Hoens, Microsoft; Jian Jiao, Microsoft Corporation; Haijing Wang, Microsoft Corporation; Dong Yu, Microsoft Research; JC Mao, Microsoft Corporation
Inferring Network Effects from Observational Data
Author(s): David Arbour*, University of Massachusetts Am; Dan Garant, University of Massachusetts Amherst; David Jensen, UMass Amherst
A Closed-Loop Approach in Data-Driven Resource Allocation to Improve Network User Experience
Author(s): Yanan Bao*, University of California, Davi; Huasen Wu, UC Davis; Xin Liu, UC Davis
Towards Robust and Versatile Causal Discovery for Business Applications
Author(s): Giorgos Borboudakis*, University of Crete; Ioannis Tsamardinos,
Causal Clustering for 1-Factor Measurement Models
Author(s): Erich Kummerfeld*, University of Pittsburgh; Joseph Ramsey, Carnegie Mellon University
Interpretable Decision Sets: A Joint Framework for Description and Prediction
Author(s): Himabindu Lakkaraju*, Stanford University; Stephen Bach, Stanford University; Jure Leskovec, Stanford University
Compressing Convolutional Neural Networks in the Frequency Domain
Author(s): Wenlin Chen*, Washington University; James Wilson, University of Edinburgh; Stephen Tyree, NVIDIA; Kilian Weinberger, Cornell; Yixin Chen,
Optimal Reserve Prices in Upstream Auctions: Empirical Application on Online Video Advertising
Author(s): Miguel Angel Alcobendas Lisbona*, Yahoo Inc; Kuang-chih Lee, Yahoo; Sheide Chammas, Yahoo
Subjectively Interesting Component Analysis: Data Projections that Contrast with Prior Expectations
Author(s): Bo Kang*, Ghent University; Jefrey Lijffijt, Ghent University; Raul Santos-Rodriguez, University of Bristol; Tijl De Bie, Ghen University
Images Don’t Lie: Transferring Deep Visual Semantic Features to Large-Scale Multimodal Learning to R
Author(s): Corey Lynch, ; Kamelia Aryafar*, Etsy Inc.; Josh Attenberg, Etsy
Online Feature Selection: A Limited-Memory Substitution Algorithm and its Asynchronous Parallel Vari
Author(s): Haichuan Yang*, University of Rochester; Ryohei Fujimaki, NEC Laboratories America; Yukitaka Kusumura, NEC lab; Ji Liu, University of Rochester
Just One More: Modeling Binge Watching Behavior
Author(s): William Trouleau, EPFL; Azin Ashkan*, Technicolor; Weicong Ding, Technicolor Research; Brian Eriksson, Technicolor
Multi-Task Feature Interaction Learning
Author(s): KAIXIANG LIN*, Michigan State University; Jianpeng Xu, Michigan State University; Shuiwang Ji, Washington State University; Jiayu Zhou, Michigan State University

Comments