Publication

Export 897 results:
2023
Xu, M., Rangamani, A., Liao, Q., Galanti, T. & Poggio, T. Dynamics in Deep Classifiers trained with the Square Loss: normalization, low rank, neural collapse and generalization bounds. Research (2023). doi:10.34133/research.0024PDF icon research.0024.pdf (4.05 MB)
Azami, H. et al. EEG Entropy in REM Sleep as a Physiologic Biomarker in Early Clinical Stages of Alzheimer’s Disease. Journal of Alzheimer's Disease 91, 1557 - 1572 (2023).
Bricken, T., Schaeffer, R., Olshausen, B. & Kreiman, G. Emergence of Sparse Representations from Noise. ICML 2023 (2023). at <https://openreview.net/pdf?id=cxYaBAXVKg>
Houlihan, S. Dae, Kleiman-Weiner, M., Hewitt, L. B., Tenenbaum, J. B. & Saxe, R. Emotion prediction as computation over a generative theory of mind. Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences 381, (2023).PDF icon houlihan2023computedappraisals.pdf (2.37 MB)
Lee, M. J. & DiCarlo, J. J. An empirical assay of view-invariant object learning in humans and comparison with baseline image-computable models. bioRxiv (2023). at <https://www.biorxiv.org/content/10.1101/2022.12.31.522402v1>
Meanti*, G. et al. Estimating Koopman operators with sketching to provably learn large scale dynamical systems. 37th Conference on Neural Information Processing Systems (NeurIPS 2023) (2023). at <https://proceedings.neurips.cc/paper_files/paper/2023/file/f3d1e34a15c0af0954ae36a7f811c754-Paper-Conference.pdf>
Vega, C., Molinari, C., Rosasco, L. & Villa, S. Fast iterative regularization by reusing dataAbstract. Journal of Inverse and Ill-posed Problems (2023). doi:10.1515/jiip-2023-0009
Rangamani, A., Lindegaard, M., Galanti, T. & Poggio, T. Feature learning in deep classifiers through Intermediate Neural Collapse. (2023).PDF icon Feature_Learning_memo.pdf (2.16 MB)
Rangamani, A., Rosasco, L. & Poggio, T. For interpolating kernel machines, minimizing the norm of the ERM solution maximizes stability. Analysis and Applications 21, 193 - 215 (2023).
Srinivasan, R. Francesco et al. Forward learning with top-down feedback: empirical and analytical characterization. arXiv (2023). at <https://arxiv.org/abs/2302.05440>
Caldarelli, E., Chatalic, A., Colom´e, A. `a, Rosasco, L. & Torras, C. Heteroscedastic Gaussian Processes and Random Features: Scalable Motion Primitives with Guarantees. 7th Conference on Robot Learning (CoRL 2023 (2023). at <https://proceedings.mlr.press/v229/caldarelli23a/caldarelli23a.pdf>
Feliciano-Ramos, P. A., Galazo, M., Penagos, H. & Wilson, M. Hippocampal memory reactivation during sleep is correlated with specific cortical states of the retrosplenial and prefrontal cortices. Learning & Memory 30, 221 - 236 (2023).
Gan, Y. & Poggio, T. A. A Homogeneous Transformer Architecture. (2023).PDF icon CBMM-Memo-143.pdf (1.07 MB)
Chen, Z. Sage & Wilson, M. A. How our understanding of memory replay evolves. Journal of Neurophysiology 129, 552 - 580 (2023).
Singhal, U. et al. How to Guess a Gradient. arXiv (2023). at <https://arxiv.org/abs/2312.04709>
Villa, S., Matet, S., Vũ, B. Công & Rosasco, L. Implicit regularization with strongly convex bias: Stability and acceleration. Analysis and Applications 21, 165 - 191 (2023).
Woo, B. M. & Spelke, E. S. Infants and toddlers leverage their understanding of action goals to evaluate agents who help others. Child Development (2023). doi:10.1111/cdev.13895
Xu, M. et al. The Janus effects of SGD vs GD: high noise and low rank. (2023).PDF icon Updated with appendix showing empirically that the main results extend to deep nonlinear networks (2.95 MB)PDF icon Small updates...typos... (616.82 KB)
Singh, P. et al. Learning to Learn: How to Continuously Teach Humans and Machines . International Conference on Computer Vision (ICCV), 2023 (2023). at <https://openaccess.thecvf.com/content/ICCV2023/html/Singh_Learning_to_Learn_How_to_Continuously_Teach_Humans_and_Machines_ICCV_2023_paper.html>
Allen, K. R. et al. Lifelong learning of cognitive styles for physical problem-solving: The effect of embodied experienceAbstract. Psychonomic Bulletin & Review (2023). doi:10.3758/s13423-023-02400-4
Tuckute, G., Feather, J., Boebinger, D. & McDermott, J. H. Many but not all deep neural network audio models capture brain responses and exhibit correspondence between model stages and brain regions. PLOS Biology 21, e3002366 (2023).
Aghajan, Z. M., Kreiman, G. & Fried, I. Minute-scale periodicity of neuronal firing in the human entorhinal cortex. Cell Reports 42, 113271 (2023).PDF icon 1-s2.0-S2211124723012834-main.pdf (5.33 MB)
Feather, J., Leclerc, G., Mądry, A. & McDermott, J. H. Model metamers reveal divergent invariances between biological and artificial neural networks. Nature Neuroscience (2023). doi:10.1038/s41593-023-01442-0
Schiatti, L. et al. Modeling Visual Impairments with Artificial Neural Networks: a Review. International Conference on Computer Vision 2023 (2023). at <https://openaccess.thecvf.com/content/ICCV2023W/ACVR/html/Schiatti_Modeling_Visual_Impairments_with_Artificial_Neural_Networks_a_Review_ICCVW_2023_paper.html>
Tomov, M. S., Tsividis, P. A., Pouncy, T., Tenenbaum, J. B. & Gershman, S. J. The neural architecture of theory-based reinforcement learning. Neuron 111, 1331 - 1344.e8 (2023).

Pages