Giulio Biroli

Artificial Intelligence · 2004–2021

A researcher in the Science corpus: 17 papers; trusts 99 researchers and is trusted by 25 researchers here, as inferred from the citation graph.

Subfields

Artificial Intelligence — 188 citations into it; #35,195 of 35,345 by trust here, #7,010 by citations
Scaling & Learning Theory — 119 citations into it; #214 of 428 by trust here, #155 by citations
Optimization & Training — 111 citations into it
Materials Chemistry — 108 citations into it; #916 of 11,513 by trust here, #3,247 by citations
Computer Vision and Pattern Recognition — 94 citations into it
Condensed Matter Physics — 72 citations into it; #143 of 1,948 by trust here, #231 by citations
Model Architectures — 62 citations into it
Statistical and Nonlinear Physics — 51 citations into it

Whom Giulio Biroli trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

Who trusts Giulio Biroli overall

Papers from Giulio Biroli's perspective

Ordered by how strongly the researchers Giulio Biroli trusts endorse each paper. Same corpus, a different order for every researcher.

Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
ImageNet classification with deep convolutional neural networks
Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
Gradient-based learning applied to document recognition
Learning Multiple Layers of Features from Tiny Images
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
Long Short-Term Memory
Attention is All you Need (Neural Information Processing Systems)
ImageNet: A large-scale hierarchical image database
Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)

Their papers

ConViT: improving vision transformers with soft convolutional inductive biases (2021) — 1,066 citations
Scaling description of generalization with number of parameters in deep learning (2019) — 214 citations
Finding the Needle in the Haystack with Convolutions: on the benefits of architectural bias (2019) — 37 citations
A jamming transition from under- to over-parametrization affects generalization in deep learning (2018) — 160 citations
Triple descent and the two kinds of overfitting: where and why do they appear? (2020) — 91 citations
Theoretical perspective on the glass transition and amorphous materials (2010) — 1,612 citations
Dynamical Heterogeneities in Glasses, Colloids, and Granular Media (2011) — 686 citations
Diverging length scale and upper critical dimension in the Mode-Coupling Theory of the glass transition (2004) — 135 citations
Comparing dynamics: deep neural networks versus glassy systems (2018) — 131 citations
Thermodynamic signature of growing amorphous order in glass-forming liquids (2008) — 285 citations
Direct Experimental Evidence of a Growing Length Scale Accompanying the Glass Transition (2005) — 647 citations
The jamming transition as a paradigm to understand the loss landscape of deep neural networks (2018) — 157 citations
The Random First-Order Transition Theory of Glasses: a critical assessment (2009) — 133 citations
Spatiotemporal hierarchy of relaxation events, dynamical heterogeneities, and structural reorganization in a supercooled liquid. (2009) — 139 citations
Marginally stable equilibria in critical ecosystems (2017) — 154 citations
Numerical implementation of dynamical mean field theory for disordered systems: application to the Lotka–Volterra model of ecosystems (2019) — 122 citations
A jamming transition from under- to over-parametrization affects loss landscape and generalization (2018) — 59 citations