All Publications
2024
CBMM Memo No.
145
“Compositional Sparsity of Learnable Functions”. 2024. CBMM-Memo-145.pdf (1.25 MB) ,
CBMM Funded
2023
CBMM Memo No.
144
“The Janus effects of SGD vs GD: high noise and low rank”. 2023. The_Janus_effects_of_SGD_vs_GD__high_noise_and_low_rank-4.pdf (2.83 MB) Updated with appendix showing empirically that the main results extend to deep nonlinear networks (2.95 MB) ,
CBMM Funded
“Norm-based Generalization Bounds for Sparse Neural Networks”, in NeurIPS 2023, New Orleans, 2023. NeurIPS-2023-norm-based-generalization-bounds-for-sparse-neural-networks-Paper-Conference.pdf (577.69 KB) ,
CBMM Funded
“Many but not all deep neural network audio models capture brain responses and exhibit correspondence between model stages and brain regions”, PLOS Biology, vol. 21, no. 12, p. e3002366, 2023. ,
CBMM Funded
“Minute-scale periodicity of neuronal firing in the human entorhinal cortex”, Cell Reports, vol. 42, no. 11, p. 113271, 2023. 1-s2.0-S2211124723012834-main.pdf (5.33 MB) ,
CBMM Funded
“Perception of 3D shape integrates intuitive physics and analysis-by-synthesis”, Nature Human Behaviour, 2023. ,
CBMM Funded
“Model metamers reveal divergent invariances between biological and artificial neural networks”, Nature Neuroscience, 2023. ,
CBMM Funded
Cervelli menti algoritmi. Sperling & Kupfer, 2023, p. 272. ,
CBMM Funded
CBMM Memo No.
143
“A Homogeneous Transformer Architecture”. 2023. CBMM-Memo-143.pdf (1.07 MB) ,
CBMM Funded
“Non-commitment in mental imagery”, Cognition, vol. 238, p. 105498, 2023. ,
CBMM Funded
“System Identification of Neural Systems: If We Got It Right, Would We Know?”, Proceedings of the 40th International Conference on Machine Learning, PMLR, vol. 202. pp. 12430-12444, 2023. han23d.pdf (797.48 KB) ,
CBMM Funded
“Emotion prediction as computation over a generative theory of mind”, Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, vol. 381, no. 2251, 2023. houlihan2023computedappraisals.pdf (2.37 MB) ,
CBMM Funded
CBMM Memo No.
142
“Skip Connections Increase the Capacity of Associative Memories in Variable Binding Mechanisms”. 2023. CBMM-Memo-142.pdf (1.64 MB) ,
CBMM Funded
“Physics informed machine learning for wind speed prediction”, Energy, vol. 268, p. 126628, 2023. ,
CBMM Funded
“Sparse distributed memory is a continual learner”, International Conference on Learning Representations. Kigali, Rwanda, Africa, 2023. 6086_sparse_distributed_memory_is_a.pdf (13.3 MB) ,
CBMM Funded
“Using artificial neural networks to ask ‘why’ questions of minds and brains”, Trends in Neurosciences, vol. 46, no. 3, pp. 240 - 254, 2023. ,
CBMM Related
“Preliminary evidence for selective cortical responses to music in one‐month‐old infants”, Developmental Science, 2023. Developmental Science - 2023 - Kosakowski - Preliminary evidence for selective cortical responses to music in one‐month‐old.pdf (2.6 MB) ,
CBMM Funded
“The neural architecture of theory-based reinforcement learning”, Neuron, vol. 111, no. 8, pp. 1331 - 1344.e8, 2023. ,
CBMM Related
CBMM Memo No.
141
“Feature learning in deep classifiers through Intermediate Neural Collapse”. 2023. Feature_Learning_memo.pdf (2.16 MB) ,
CBMM Funded
“CNNs reveal the computational implausibility of the expertise hypothesis”, iScience, vol. 26, no. 2, p. 105976, 2023. ,
CBMM Funded
“Neural coding: Stimulating cortex to alter visual perception”, Current Biology, vol. 33, no. 3, pp. R117 - R118, 2023. ,
CBMM Funded
“An adversarial collaboration protocol for testing contrasting predictions of global neuronal workspace and integrated information theory”, PLOS ONE, vol. 18, no. 2, p. e0268577, 2023. journal.pone_.0268577.pdf (1.99 MB) ,
CBMM Related
“Forward learning with top-down feedback: empirical and analytical characterization”, arXiv, 2023. ,
CBMM Funded
“Zero-shot linear combinations of grounded social interactions with Linear Social MDPs”, in Proceedings of the 37th AAAI Conference on Artificial Intelligence (AAAI), 2023. ,
CBMM Funded
“BrainBERT: Self-supervised representation learning for Intracranial Electrodes”, International Conference on Learning Representations. Kigali, Rwanda, Africa, 2023. 985_brainbert_self_supervised_repr.pdf (9.71 MB) ,
CBMM Funded