Apostolos Modas

Our paper raises ethical considerations in visual data collection, and offers perspectives on how to think about them from the start. Work led by Jerone Andrews! With @dorazhao9 , myself, @amodas_ ,@SciOrestis ,@alicexiang Paper: arxiv.org/abs/2302.03629 #NeurIPS2023

A neural anisotropic view of underspecification in deep learning deepai.org/publication/a-… by Guillermo Ortiz-Jiménez et al. including @pafrossard #MachineLearning #DeepLearning

Interested in adv. robustness beyond security, or how adv. examples can help us understand deep learning? 🤔 Check our review paper “Optimism in the face of adversity”, just published in the Proc. IEEE 🚀 💎Xplore: bit.ly/3qz3men 📄arXiv: bit.ly/3s5Vz8a

Why do state-of-the-art NNs only generalise on a few linearly separable problems? 🤓 Figure it out at our poster today at 6-8pm CET (9-11am PST) @ Town E1, spot D3 #NeurIPS2020 🏡 Gather town: bit.ly/2JLScCQ

Want to know what happens when you train a CNN on frequency reversed samples and what this has to do with robustness? Then join us at our poster in #NeurIPS2020 🤓 “Hold me tight! Influence of discriminative features on deep network boundaries” 📄: bit.ly/36TlNmO

Seeing the glass as half full🥛Optimism in the Face of Adversity arxiv.org/pdf/2010.09624… In this pre-print we talk about what adv. examples reveal about the geometry of deep nets and how other topics in ML can benefit from such insights. With @gortizji , @modasapo, @pafrossard