Jonas Mueller

Overinterpretation reveals image classification model pathologies

2020 · arXiv (Cornell University)

Image classifiers are typically scored on their test set accuracy, but high accuracy can mask a subtle type of model failure. We find that high scoring convolutional neural networks (CNNs) on popular benchmarks exhibit troubling …

Siamese Recurrent Architectures for Learning Sentence Similarity

2016 · Proceedings of the AAAI Conference on Artificial Intelligence

We present a siamese adaptation of the Long Short-Term Memory (LSTM) network for labeled data comprised of pairs of variable-length sequences. Our model is applied to assess semantic similarity between sentences, where we exceed state …