Publication
Theories of Deep Learning: Approximation, Optimization and Generalization . TECHCON 2019 (2019).
Object-Oriented Deep Learning. (2017).
CBMM-Memo-070.pdf (963.54 KB)
Streaming Normalization: Towards Simpler and More Biologically-plausible Normalizations for Online and Recurrent Learning. (2016).
CBMM-Memo-057.pdf (1.27 MB)
Can a biologically-plausible hierarchy effectively replace face detection, alignment, and recognition pipelines?. (2014).
CBMM-Memo-003.pdf (963.66 KB)
Why does deep and cheap learning work so well?. Journal of Statistical Physics 168, 1223–1247 (2017).
1608.08225.pdf (2.14 MB)
Critical Behavior from Deep Dynamics: A Hidden Dimension in Natural Language. arXiv.org (2016).
Critical Behavior from Deep Dynamics: A Hidden Dimension in Natural Language (1.64 MB)
A Bayesian nonparametric approach for uncovering rat hippocampal population codes during spatial navigation. Journal of Neuroscience Methods 263, (2016).
Journal of Neuroscience Methods (2.27 MB)
A framework for studying synaptic plasticity with neural spike train data. Neural Information Processing Systems (2014).
5274-a-framework-for-studying-synaptic-plasticity-with-neural-spike-train-data.pdf (4.6 MB)
A Nonparametric Bayesian Approach to Uncovering Rat Hippocampal Population Codes During Spatial Navigation. (2014).
CBMM-Memo-027.pdf (9.44 MB)
Inferring structured connectivity from spike trains under negative-binomial generalized linear models. (2015).
cosyne2015a.pdf (384.83 KB)
Origins of the concepts cause, cost, and goal in prereaching infants. PNAS (2019). doi:https://doi.org/10.1073/pnas.1904410116
Author's last draft (2.58 MB)
People's perceptions of others’ risk preferences. Cognitive Science Society (2019).
risk_cogsci_2019_final.pdf (899.8 KB)
Pre-reaching infants expect causal agents to act efficiently without motor training. 20th Biennial International Conference on Infant Studies (ICIS) (2016).
Ten-month-old infants infer value from effort. Society for Research in Child Development (2017).
Ten-month-old infants infer the value of goals from the costs of actions. Science 358, 1038-1041 (2017).
ivc_full_preprint_withsm.pdf (1.6 MB)
Hard choices: Children’s understanding of the cost of action selection. . Cognitive Science Society (2019).
phk_cogsci_2019_final.pdf (276.14 KB)
Recurrent Multimodal Interaction for Referring Image Segmentation. (2018).
CBMM-Memo-079.pdf (10.16 MB)
Six-month-old infants represent action efficiency on a continuous scale. 9th Biennial Meeting of the Cognitive Development Society (CDS) (2015).
Timing, timing, timing: Fast decoding of object inforrmation from intracranial field potentials in human visual cortex. (2009). at <http://klab.tch.harvard.edu/resources/liuetal_timing3.html>
Dangerous Ground: One-Year-Old Infants are Sensitive to Peril in Other Agents’ Action PlansAbstract. Open Mind 6, 211 - 231 (2022).
Continuous representations of action efficiency in infancy. CEU Conference on Cognitive Development (BCCCD16) (2016).
Origins of the concepts cause, cost, and goal in prereaching infants. Cognitive Development Society (2019).
liu_etal_lumi_cds2019_final.pdf (22.95 MB)
Six-month-old infants expect agents to minimize the cost of their actions. Cognition 160, 35-42 (2017).
]