He Zhang  

Data Scientist at Verto Analytics Inc. (2014 - Present)

Doctor of Science, Machine Learning & Image Processing

Project & Research Areas

• Machine Learning, Data Mining
• Cluster Analysis, Matrix Factorization
• Image Classification & Retrieval, Affective Image Analysis

From 2008 to 2010 I mainly worked as a project researcher for the EU-FP7 PinView project, supervised by Senior Scientist Dr. Jorma Laaksonen. After 2011, my research focused on data cluster analysis based on Nonnegative Matrix Factorization models, supervised by Aalto Distinguished Professor Erkki Oja, IEEE Life Fellow. Since 2014, I have been working as a Data Scientist at Verto Analytics - a Finnish pioneer in Digital Media Research and Measurement Industry.

Computer Skills

• MATLAB, Python, MySQL / PostgreSQL, C / C++, Perl, JavaScript, LaTeX, Excel


• Mac OS X, Linux, Windows

Short Bio in Chinese

• 张鹤，数据分析师，数据科学家，芬兰阿尔托大学 (Aalto)－信息与计算机科学博士 (PhD in Machine Learning)；


• 拥有8年以上机器学习，数据挖掘，图像处理的项目与科研经历，以及卓越的英语口语及书面表达能力；


• 现工作职责包括: 移动互联网多元媒体数据分析与融合，移动端（手机，Pad）图像识别算法开发，以及撰写市场分析报告。

Education Background

• I obtained my PhD in Computer Science (machine learning) in 2014 from Aalto University School of Science, Finland. My PhD supervisor was Aalto Distinguished Professor Erkki Oja (IEEE Life Fellow), and my instructor was Docent Dr. Zhirong Yang.


• I completed my Master's (2004-2007) and Bachelor's degrees (2000-2004) from Jilin Uinversity College of Communication Engineering, China. My Master's thesis focused on developing high-dimensional orthogonal matrix transformation techniques for digital image compression.

Journal Articles

• He Zhang, Mehmet Gönen, Zhirong Yang, and Erkki Oja. Understanding Emotional Impact of Images Using Bayesian Multiple Kernel Learning. Neurocomputing, 165: 3-13, 2015. [PDF_doi]


• He Zhang, Zhirong Yang and Erkki Oja. Improving Cluster Analysis By Co-initializations. Pattern Recognition Letters, 45: 71-77, 2014. [PDF_doi] [Supplemental Document] [Datasets and Matlab Codes]


• He Zhang, Zhirong Yang and Erkki Oja. Adaptive Multiplicative Updates for Quadratic Nonnegative Matrix Factorization. Neurocomputing, 134: 206-213, 2014 (Accepted with minor revision).[PDF_doi] [Datasets and Matlab Codes]

Conference Papers

• He Zhang, Mehmet Gönen, Zhirong Yang, and Erkki Oja. Predicting Emotional States of Images Using Bayesian Multiple Kernel Learning. In Proceedings of the 20th International Conference on Neural Information Processing (ICONIP2013), Daegu, South Korea, 2013. Oral presentation. [final PDF]


• He Zhang, Zhirong Yang, Mehmet Gönen, Markus Koskela, Jorma Laaksonen, Timo Honkela, and Erkki Oja. Affective Abstract Image Classification and Retrieval Using Multiple Kernel Learning. In Proceedings of the 20th International Conference on Neural Information Processing (ICONIP2013), Daegu, South Korea, 2013. Oral presentation. [final PDF]


• He Zhang, Zhirong Yang, and Erkki Oja. Adaptive Multiplicative Updates for Projective Nonnegative Matrix Factorization. In Proceedings of the 19th International Conference on Neural Information Processing (ICONIP2012), Doha, Qatar, 2012. Oral presentation. [final PDF]


• Zhirong Yang, He Zhang, and Erkki Oja. Online Projective Nonnegative Matrix Factorization for Large Datasets. In Proceedings of the 19th International Conference on Neural Information Processing (ICONIP2012), Doha, Qatar, 2012. Oral presentation. [final PDF]


• He Zhang, Tele Hao, Zhirong Yang, and Erkki Oja. Pairwise Clustering with t-PLSI. In Proceedings of the 22nd International Conference on Artificial Neural Networks (ICANN2012), Lausanne, Switzerland, 2012. Travel Grant Award. [final PDF]


• He Zhang, Mats Sjöberg, Jorma Laaksonen, and Erkki Oja. A Multimodal Information Collector for Content-Based Image Retrieval System. In Proceedings of the 18th International Conference on Neural Information Processing (ICONIP2011), Shanghai, China, 2011. Oral presentation [final PDF]


• He Zhang, Eimontas Augilius, Timo Honkela, Jorma Laaksonen, Hannes Gamper, and Henok Alene. Analyzing Emotional Semantics of Abstract Art Using Low-Level Image Features. In Proceedings of the 10th International Conference on Advances in Intelligent Data Analysis (IDA2011), Porto, Portugal, 2011. Oral presentation. [final PDF]


• He Zhang, Teemu Ruokolainen, Jorma Laaksonen, Christina Hochleitner, and Rudolf Traunmüller. Gaze-and Speech-Enhanced Content-Based Image Retrieval in Image Tagging. In Proceedings of the 21st International Conference on Artificial Neural Networks (ICANN2011), Espoo, Finland, 2011. Poster presentation. [final PDF]


• Zhirong Yang, He Zhang, Zhijian Yuan, and Erkki Oja. Kullback-Leibler Divergence for Nonnegative Matrix Factorization. In Proceedings of the 21st International Conference on Artificial Neural Networks (ICANN2011), Espoo, Finland, 2011. [final PDF]

Technical Reports

• He Zhang, Markus Koskela, and Jorma Laaksonen. Report on Forms of Enriched Relevance Feedback. Technical Report TKK-ICS-R10, Helsinki University of Technology, Department of Information and Computer Science. Presented at PinView meeting, University College London, 2008. [PDF]


• He Zhang, Mats Sjöberg, and Jorma Laaksonen. Browser Extension for Pointer Track Feedback. PinView Deliverables. Presented at PinView meeting, Leoben University, Austria, 2008. [PDF] [Download the FireFox extention software]


• Christina Hochleitner, Rudolf Traunmüller, Teemu Ruokolainen, and He Zhang. Archiving with Supported Tagging. PinView Deliverables. Celum Company, Austria, 2011. [PDF]

These reports are based on the PinView project, whose aim is to facilitate a prototype of a proactive personal information navigator that can infer the user's preference from his explicit and implicit feedback signals (eye movements, pointer traces and clicks, speech).

Doctoral Dissertation

I successfully defended my PhD thesis, titled Advances in Nonnegative Matrix Decomposition with Application to Cluster Analysis, on September 19, 2014. My opponent was Professor A. Taylan Cemgil from Bogazici University, Istanbul, Turkey. More Detailed information can be found at the website of Aalto University Library.

Academic Services

• PC member for ICANN2014, Membership of ENNS.


• Reviewers: IEEE Transactions on Neural Networks and Learning Systems, Information Sciences, Neurocomputing, Optical Engineering, International Journal of Machine Learning and Cybernetics, ICANN conferences, etc.

Language Skills

• English: Excellent in writing and speaking; IELTS test (2006) overall 7.5 (Listening 7.5, Reading 8.5, Writing 7.0, Speaking 7.0); Chinese-English Translator and Interpretor (2005-2007), with Band 3 certificate issued by the Chinese Human Resource Ministry


• Finnish: Basic (with Permanent Finnish Resident Permit from 2012)


• Chinese: Native (Mandarin speaker)