Interactive Machine Learning via a GPU-accelerated Toolkit

Machine learning is growing in importance in industry, sciences, and many other fields. In many and perhaps most of these applications, users need to trade off competing goals. Machine learning, however, has evolved around the optimization of a single, usually narrowly-defined criterion. In most cases, an expert makes (or should be making) trade-offs between these criteria which requires high-level (human) intelligence. With interactive customization and optimization the expert can incorporate secondary criteria into the model-generation process in an interactive way. In this paper we develop the techniques to perform customized and interactive model optimization, and demonstrate the approach on several examples. The keys to our approach are (i) a machine learning architecture which is modular and supports primary and secondary loss functions, while users can directly manipulate its parameters during training (ii) high-performance training so that non-trivial models can be trained in real-time (using roofline design and GPU hardware), and (iii) highly-interactive visualization tools that support dynamic creation of visualizations and controls to match various optimization criteria.

[1]  Jeffrey Heer,et al.  D³ Data-Driven Documents , 2011, IEEE Transactions on Visualization and Computer Graphics.

[2]  Jerry Alan Fails,et al.  Interactive machine learning , 2003, IUI '03.

[3]  Samuel Williams,et al.  Roofline: an insightful visual performance model for multicore architectures , 2009, CACM.

[4]  Jeffrey Heer,et al.  SpanningAspectRatioBank Easing FunctionS ArrayIn ColorIn Date Interpolator MatrixInterpola NumObjecPointI Rectang ISchedu Parallel Pause Scheduler Sequen Transition Transitioner Transiti Tween Co DelimGraphMLCon IData JSONCon DataField DataSc Dat DataSource Data DataUtil DirtySprite LineS RectSprite , 2011 .

[5]  Francis R. Bach,et al.  Online Learning for Latent Dirichlet Allocation , 2010, NIPS.

[6]  Sebastian Nowozin,et al.  Learning Step Size Controllers for Robust Neural Network Training , 2016, AAAI.

[7]  H. Sebastian Seung,et al.  Algorithms for Non-negative Matrix Factorization , 2000, NIPS.

[8]  Yong Jae Lee,et al.  AverageExplorer: interactive exploration and alignment of visual data collections , 2014, ACM Trans. Graph..

[9]  Chong Wang,et al.  Reading Tea Leaves: How Humans Interpret Topic Models , 2009, NIPS.

[10]  Yi Yang,et al.  User-directed Non-Disruptive Topic Model Update for Effective Exploration of Dynamic Content , 2015, IUI.

[11]  Maya Cakmak,et al.  Power to the People: The Role of Humans in Interactive Machine Learning , 2014, AI Mag..

[12]  Desney S. Tan,et al.  Using Multiple Models to Understand Data , 2011, IJCAI.

[13]  John F. Canny,et al.  Big data analytics with small footprint: squaring the cloud , 2013, KDD.

[14]  Yoram Singer,et al.  Adaptive Subgradient Methods for Online Learning and Stochastic Optimization , 2011, J. Mach. Learn. Res..

[15]  Leon A. Gatys,et al.  Image Style Transfer Using Convolutional Neural Networks , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Trevor Darrell,et al.  DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition , 2013, ICML.

[17]  Martin Wattenberg,et al.  Direct-Manipulation Visualization of Deep Networks , 2017, ArXiv.

[18]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[19]  Michael I. Jordan,et al.  Latent Dirichlet Allocation , 2001, J. Mach. Learn. Res..

[20]  Quentin Pleple,et al.  Interactive Topic Modeling , 2013 .

[21]  Ryan P. Adams,et al.  Gradient-based Hyperparameter Optimization through Reversible Learning , 2015, ICML.

[22]  Jasper Snoek,et al.  Practical Bayesian Optimization of Machine Learning Algorithms , 2012, NIPS.

[23]  Andrew Y. Ng,et al.  Learning Feature Representations with K-Means , 2012, Neural Networks: Tricks of the Trade.

[24]  Desney S. Tan,et al.  EnsembleMatrix: interactive visualization to support machine learning with multiple classifiers , 2009, CHI.

[25]  Shi Zhong,et al.  Efficient online spherical k-means clustering , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[26]  Timothy Baldwin,et al.  Automatic Evaluation of Topic Coherence , 2010, NAACL.

[27]  D. Botstein,et al.  Cluster analysis and display of genome-wide expression patterns. , 1998, Proceedings of the National Academy of Sciences of the United States of America.

[28]  Hema Raghavan,et al.  InterActive Feature Selection , 2005, IJCAI.

[29]  Deng Cai,et al.  Topic modeling with network regularization , 2008, WWW.

[30]  Ameet Talwalkar,et al.  Efficient Hyperparameter Optimization and Infinitely Many Armed Bandits , 2016, ArXiv.

[31]  Marcin Andrychowicz,et al.  Learning to learn by gradient descent by gradient descent , 2016, NIPS.

[32]  Ben Shneiderman,et al.  Interactively Exploring Hierarchical Clustering Results , 2002, Computer.

[33]  Jeffrey Heer,et al.  Termite: visualization techniques for assessing textual topic models , 2012, AVI.

[34]  Desney S. Tan,et al.  Performance and Preferences: Interactive Refinement of Machine Learning Procedures , 2012, AAAI.

[35]  John Canny,et al.  SAME but Different: Fast and High Quality Gibbs Parameter Estimation , 2014, KDD.

[36]  Edwin V. Bonilla,et al.  Improving Topic Coherence with Regularized Topic Models , 2011, NIPS.

[37]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[38]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[39]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.

[40]  Yoshua Bengio,et al.  Random Search for Hyper-Parameter Optimization , 2012, J. Mach. Learn. Res..