Accelerating innovation through analogy mining Hope et al., KDD'17 Today's choice won a best paper award at KDD'17. It's a really interesting twist on information retrieval, building on a foundation of GloVe and word vectors to create purpose and mechanism vectors for a corpus of product descriptions. Using these vectors, the authors show how to … Continue reading Accelerating innovation through analogy mining

Adversarial examples for evaluating reading comprehension systems Jia & Liang, EMNLP 2017 We've now seen a number of papers investigating adversarial examples for images. In today's paper choice, Jia and Liang explore adversarial examples for text samples in the context of reading comprehension systems. The results are frankly a bit of a wake-up call for … Continue reading Adversarial examples for evaluating reading comprehension systems

Universal adversarial perturbations Moosavi-Dezfooli et al., CVPR 2017. I'm fascinated by the existence of adversarial perturbations - imperceptible changes to the inputs to deep network classifiers that cause them to mis-predict labels. We took a good look at some of the research into adversarial images earlier this year, where we learned that all deep networks … Continue reading Universal adversarial perturbations

Learning transferable architectures for scalable image recognition Zoph et al., arXiv 2017 Things move fast in the world of deep learning! It was only a few months ago that we looked at 'Neural architecture search with reinforcement learning.' In that paper, Zoph et al., demonstrate that just like we once designed features by hand but … Continue reading Learning transferable architectures for scalable image recognition