Jason Zhi Liang
PhD Student in the Computer Science Department
Email: jasonzliang@utexas.edu
Resume/CVGithubGoogle Scholar

Research:
I am a computer science PhD student at UT Austin. My general research interests are deep learning, evolutionary computation, meta-learning, neural networks, and artificial intelligence.
My current research is about developing evolutionary algorithms for large scale, efficient optimization of the hyperparameters and architectures of deep neural networks. I spent the entirety of 2016 interning at Sentient Technologies, where I constructed a distributed framework capable of evaluating and evolving thousands of different neural network architectures at the same time. Please see my blog post here for more details.

Projects:

[1] Miscellaneous machine learning related assignments
Source Code: https://github.com/jasonzliang/scalableMLAssignments
[2] Stacked denoising autoencoders (Deep Learning), trained using SGD and genetic algorithms
Source Code: https://github.com/jasonzliang/autoencoder
Report: http://users.ices.utexas.edu/~keith/files/autoencoder/final_report/autoencoder.pdf

Publications:

[1] Liang, Jason Zhi, et al. "Image Based Localization in Indoor Environments." Computing for Geospatial Research and Application (COM. Geo), 2013 Fourth International Conference on. IEEE, 2013. c Link: http://www-video.eecs.berkeley.edu/papers/jasonzliang/latest.pdf
[2] Liang, Jason Zhi, et al. "Reduced-complexity data acquisition system for image-based localization in indoor environments." Indoor Positioning and Indoor Navigation (IPIN), 2013 International Conference on. IEEE, 2013.
Link: http://www-video.eecs.berkeley.edu/papers/jasonzliang/indoor_localization_paper_20131021.pdf
[3] Liang, Jason Zhi, et al. "Image-Based Positioning of Mobile Devices in Indoor Environments." Multimodal Location Estimation, Sprinter Gerald Friedland, Ed (2014).
Link: http://www-video.eecs.berkeley.edu/papers/jasonzliang/multimodal_location_estimation.pdf
[4] Liang, Jason Zhi, and Risto Miikkulainen. "Evolutionary Bilevel Optimization for Complex Control Tasks." GECCO. 2015.
Link: https://www.cs.utexas.edu/~jliang/liang_gecco15.pdf