Publication
When Pigs Fly: Contextual Reasoning in Synthetic and Natural Scenes. International Conference on Computer Vision (ICCV) (2021). doi:10.1109/iccv48922.2021.00032
Bomatter_When_Pigs_Fly_Contextual_Reasoning_in_Synthetic_and_Natural_Scenes_ICCV_2021_paper.pdf (3.24 MB)
A machine learning approach to predict episodic memory formation. 2016 Annual Conference on Information Science and Systems (CISS) 539 - 544 (2016). doi:10.1109/CISS.2016.7460560
Learning scene gist with convolutional neural networks to improve object recognition. 2018 52nd Annual Conference on Information Sciences and Systems (CISS) (2018). doi:10.1109/CISS.2018.8362305
08362305.pdf (3.17 MB)
Error-driven Input Modulation: Solving the Credit Assignment Problem without a Backward Pass. Proceedings of the 39th International Conference on Machine Learning, PMLR 162, 4937-4955 (2022).
dellaferrera22a.pdf (909.91 KB)
Development of automated interictal spike detector. 40th International Conference of the IEEE Engineering in Medicine and Biology Society - EMBC 2018 (2018). at <https://embc.embs.org/2018/>
Visual Search Asymmetry: Deep Nets and Humans Share Similar Inherent Biases. NeurIPS 2021 (2021). at <https://nips.cc/Conferences/2021/Schedule?showEvent=28848>
gk8091.pdf (2.47 MB)
What can human minimal videos tell us about dynamic recognition models?. International Conference on Learning Representations (ICLR 2020) (2020). at <https://baicsworkshop.github.io/pdf/BAICS_1.pdf>
Authors' final version (516.09 KB)
Unsupervised Learning of Visual Structure using Predictive Generative Networks. International Conference on Learning Representations (ICLR) (2016). at <http://arxiv.org/pdf/1511.06380v2.pdf>
Frivolous Units: Wider Networks Are Not Really That Wide. AAAI 2021 (2021). at <https://dblp.org/rec/conf/aaai/CasperBDGSVK21.html>
1912.04783.pdf (6.69 MB)
Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning. ICLR (2017).
1605.08104.pdf (2.9 MB)
Short temporal asynchrony disrupts visual object recognition. (2014). at <http://klab.tch.harvard.edu/resources/singer_asynchrony.html>
What am I searching for?. (2018).
CBMM-Memo-096.pdf (1.74 MB)
UNSUPERVISED LEARNING OF VISUAL STRUCTURE USING PREDICTIVE GENERATIVE NETWORKS. (2015).
CBMM Memo 040_rev1.pdf (1.92 MB)
Spatiotemporal interpretation features in the recognition of dynamic images. (2018).
CBMM-Memo-094.pdf (1.21 MB)
CBMM-Memo-094-dynamic-figures.zip (1.8 MB)
fig1.ppsx (147.67 KB)
fig2.ppsx (419.72 KB)
fig4.ppsx (673.41 KB)
figS1.ppsx (587.88 KB)
figS2.ppsx (281.56 KB)
Sensitivity to Timing and Order in Human Visual Cortex. (2014).
CBMM-Memo-005.pdf (1.12 MB)
A role for recurrent processing in object completion: neurophysiological, psychophysical and computational evidence. (2014).
CBMM-Memo-009.pdf (4.21 MB)
On the Robustness of Convolutional Neural Networks to Internal Architecture and Weight Perturbations. (2017).
CBMM-Memo-065.pdf (687.76 KB)
Psychology of Learning and Motivation 70, (2019).
Single neuron studies of the human brain. Probing cognition (2014).
]