This is an old revision of the document!
Peer-reviewed publications
- Mix2Vec: Unsupervised Mixed Data Representation
Zhu C., Zhang Q., Cao L., Abrahamyan A. (2020)
IEEE 7th International Conference on Data Science and Advanced Analytics (DSAA), Sydney, NSW, Australia, 2020, pp. 118-127. Abstract. Unsupervised representation learning on mixed data is highly challenging but rarely explored. It has to tackle significant challenges related to common issues in real-life mixed data, including sparsity, dynamics and heterogeneity of attributes and values. This work introduces an effective and efficient unsupervised deep representer called Mix2Vec to automatically learn a universal representation of dynamic mixed data with the above complex characteristics. Mix2Vec is empowered with three effective mechanisms: random shuffling prediction, prior distribution matching, and structural informativeness maximization, to tackle the aforementioned challenges. These mechanisms are implemented as an unsupervised deep neural representer Mix2Vec. Mix2Vec converts complex mixed data into vector space-based representations that are universal and comparable to all data objects and transparent and reusable for both unsupervised and supervised learning tasks. Extensive experiments on four large mixed datasets demonstrate that Mix2Vec performs significantly better than state-of-the-art deep representation methods. We also empirically verify the designed mechanisms in terms of representation quality, visualization and capability of enabling better performance of downstream tasks.
- Adaptable History Biases in Human Perceptual Decisions
Abrahamyan, A., Silva L. L., Dakin S. C., Carandini M., & Gardner J. L. (2016)
Proceedings of the National Academy of Sciences, 113(25), E3548–57. More
- Mimicry and Expressiveness of an ECA in Human-Agent Interaction: Familiarity Breeds Content!
Stevens, C. J., Pinchbeck B., Lewis, T., Luerssen, M., Pfitzner, D., Powers, D., Abrahamyan, A., Leung, Y., & Gibert, G. (2016)
Computational Cognitive Science, 2(1), 1-14. More
- Low Intensity TMS Enhances Perception of Visual Stimuli
Abrahamyan, A., Clifford, C. W. G., Arabzadeh, E., & Harris, J. A. (2015)
Brain Stimulation, 8(6), 1175–1182. More
- Brain-stimulation Induced Blindsight: Unconscious Vision or Response Bias?
Lloyd, D. A., Abrahamyan, A., & Harris, J. A. (2013)
PLoS ONE, 8(12), e82828. More
- Improving Visual Sensitivity with Subthreshold Transcranial Magnetic Stimulation
Abrahamyan, A., Clifford, C. W. G., Arabzadeh, E., & Harris, J. A. (2011)
Journal of Neuroscience, 31(9), 3290–3294 More
- The effect of TMS on Visual Motion Sensitivity: An Increase in Neural Noise or a Decrease in Signal Strength?
Ruzzoli, M., Abrahamyan, A., Clifford, C. W. G., Marzi, C. A., Miniussi, C., & Harris, J. A. (2011)
Journal of Neurophysiology, 106(1), 138–143. More
- Accurate and Rapid Estimation of Phosphene Thresholds (REPT)
Abrahamyan, A., Clifford, C. W. G., Ruzzoli, M., Arabzadeh, E., & Harris, J. A. (2011)
PLoS ONE, 6(7) e22342 More
- Wired for Her Face? Male Attentional Bias for Female Faces
Okazaki, Y., Abrahamyan, A., Stevens, C. J., & Ioannides, A. A. (2010)
Brain Topography, 23(1), 14–26. More
- The Timing of Face Selectivity and Attentional Modulation in Visual Processing
Okazaki, Y., Abrahamyan, A., Stevens, C. J., & Ioannides, A. A. (2008)
Neuroscience, 152(4), 1130–1144. More
Conference Presentations
- Sensation and superstition in human perceptual decisions
Abrahamyan A, Silva LL, Dakin CD, Carandini M, Gardner JL
Stanford Neurosciences Institute Symposium, Stanford University, CA, 2015 - Naturally occurring and experimentally induced choice history biases in human observers
Abrahamyan A, Gardner JL
Neuroscience Meeting Planner, Society for Neuroscience, Abstract. San Diego, CA, 2013. - Past failures can bias human decisions
Abrahamyan A, Gardner JL
The 36th Annual Meeting of Japan Neuroscience Society, Kyoto, Japan, 2013 - Past failures bias human decisions
Abrahamyan A, Gardner JL
10th Annual Meeting, Computational and Systems Neuroscience (COSYNE) Conference Abstracts, Salt Lake City, UT, 2013 - Low intensity TMS can facilitate identification of visual stimuli
Abrahamyan A, Clifford CWG, Arabzadeh E, & Harris JA
Paper presented at the Australasian Experimental Psychology Conference, Sydney, Australia, 2012 - Improving visual sensitivity with subthreshold transcranial magnetic stimulation
Abrahamyan A, Clifford CWG, Arabzadeh E, & Harris JA
Program No. 674.14/LL7 2010 Neuroscience Meeting Planner, Society for Neuroscience, Abstract, San Diego, CA, 2010. - Low intensity transcranial magnetic stimulation can improve detection of visual stimuli
Abrahamyan A, Clifford CWG, Arabzadeh E, & Harris JA
Paper presented at the Australasian Experimental Psychology Conference, Melbourne, Australia, 2010 - Fast method for precise phosphene threshold identification in research using transcranial magnetic stimulation
Abrahamyan A, Clifford CWG, & Harris JA
Paper presented at the Australian Neuroscience Conference, Sydney, Australia, 2010 - Low intensity transcranial magnetic stimulation can improve detection of visual stimuli
Paper presented at the Australian Neuroscience Conference, Sydney, Australia, 2010