Bookmarked Snapshot (590) Files Original URL
2022-05-27 1:56PM A closer look at memorization in deep networks ❢  πŸ“„  πŸ’»  πŸ…·  πŸ††  πŸ“¦  πŸ†  πŸ…Ό  πŸ…Ά  πŸ“Ό  πŸ›   9 https://kylrth.com/paper/closer-look-at-memorization/
2022-05-27 1:56PM A sensitivity analysis of (and practitioners’ guide to) convolutional neural networks for sentence classification ❢  πŸ“„  πŸ’»  πŸ…·  πŸ††  πŸ“¦  πŸ†  πŸ…Ό  πŸ…Ά  πŸ“Ό  πŸ›   9 https://kylrth.com/paper/cnn-sentence/
2022-05-27 1:56PM kylrth.com/paper/cnn-sentence/sentence_conv.png ❢  πŸ“„  πŸ’»  πŸ…·  πŸ††  πŸ“¦  πŸ†  πŸ…Ό  πŸ…Ά  πŸ“Ό  πŸ›   4 https://kylrth.com/paper/cnn-sentence/sentence_conv.png
2022-05-27 1:56PM The consciousness prior ❢  πŸ“„  πŸ’»  πŸ…·  πŸ††  πŸ“¦  πŸ†  πŸ…Ό  πŸ…Ά  πŸ“Ό  πŸ›   9 https://kylrth.com/paper/consciousness-prior/
2022-05-27 1:56PM Cross-lingual alignment of contextual word embeddings, with applications to zero-shot dependency parsing ❢  πŸ“„  πŸ’»  πŸ…·  πŸ††  πŸ“¦  πŸ†  πŸ…Ό  πŸ…Ά  πŸ“Ό  πŸ›   10 https://kylrth.com/paper/cross-lingual-alignment-contextual/
2022-05-27 1:56PM kylrth.com/paper/cross-lingual-alignment-contextual/pca.png ❢  πŸ“„  πŸ’»  πŸ…·  πŸ††  πŸ“¦  πŸ†  πŸ…Ό  πŸ…Ά  πŸ“Ό  πŸ›   4 https://kylrth.com/paper/cross-lingual-alignment-contextual/pca.png
2022-05-27 1:56PM Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks ❢  πŸ“„  πŸ’»  πŸ…·  πŸ††  πŸ“¦  πŸ†  πŸ…Ό  πŸ…Ά  πŸ“Ό  πŸ›   9 https://kylrth.com/paper/ctc/
2022-05-27 1:56PM Data scaling laws in NMT: the effect of noise and architecture ❢  πŸ“„  πŸ’»  πŸ…·  πŸ††  πŸ“¦  πŸ†  πŸ…Ό  πŸ…Ά  πŸ“Ό  πŸ›   9 https://kylrth.com/paper/data-scaling-laws-nmt/
2022-05-27 1:56PM Deep contextualized word representations ❢  πŸ“„  πŸ’»  πŸ…·  πŸ††  πŸ“¦  πŸ†  πŸ…Ό  πŸ…Ά  πŸ“Ό  πŸ›   9 https://kylrth.com/paper/deep-contextualized-word-representations/
2022-05-27 1:56PM Deep learning ❢  πŸ“„  πŸ’»  πŸ…·  πŸ††  πŸ“¦  πŸ†  πŸ…Ό  πŸ…Ά  πŸ“Ό  πŸ›   10 https://kylrth.com/paper/deep-learning/
2022-05-27 1:56PM kylrth.com/paper/deep-learning/samoyed.png ❢  πŸ“„  πŸ’»  πŸ…·  πŸ††  πŸ“¦  πŸ†  πŸ…Ό  πŸ…Ά  πŸ“Ό  πŸ›   4 https://kylrth.com/paper/deep-learning/samoyed.png
2022-05-27 1:56PM A disciplined approach to neural network hyperparameters: part 1 ❢  πŸ“„  πŸ’»  πŸ…·  πŸ††  πŸ“¦  πŸ†  πŸ…Ό  πŸ…Ά  πŸ“Ό  πŸ›   9 https://kylrth.com/paper/disciplined-approach-to-hyperparameters/
2022-05-27 1:56PM Distributed representations of words and phrases and their compositionality ❢  πŸ“„  πŸ’»  πŸ…·  πŸ††  πŸ“¦  πŸ†  πŸ…Ό  πŸ…Ά  πŸ“Ό  πŸ›   9 https://kylrth.com/paper/distributed-representations/
2022-05-27 1:56PM The effect of model size on worst-group generalization ❢  πŸ“„  πŸ’»  πŸ…·  πŸ††  πŸ“¦  πŸ†  πŸ…Ό  πŸ…Ά  πŸ“Ό  πŸ›   9 https://kylrth.com/paper/effect-of-model-size-on-worst-group-generalization/
2022-05-27 1:56PM Experienced well-being rises with income, even above $75,000 per year ❢  πŸ“„  πŸ’»  πŸ…·  πŸ††  πŸ“¦  πŸ†  πŸ…Ό  πŸ…Ά  πŸ“Ό  πŸ›   9 https://kylrth.com/paper/experienced-well-being/
2022-05-27 1:56PM kylrth.com/paper/experienced-well-being/plot.webp ❢  πŸ“„  πŸ’»  πŸ…·  πŸ††  πŸ“¦  πŸ†  πŸ…Ό  πŸ…Ά  πŸ“Ό  πŸ›   4 https://kylrth.com/paper/experienced-well-being/plot.webp
2022-05-27 1:56PM Compositional generalization by factorizing alignment and translation ❢  πŸ“„  πŸ’»  πŸ…·  πŸ††  πŸ“¦  πŸ†  πŸ…Ό  πŸ…Ά  πŸ“Ό  πŸ›   9 https://kylrth.com/paper/factorizing-alignment-and-translation/
2022-05-27 1:56PM Google's neural machine translation system: bridging the gap between human and machine translation ❢  πŸ“„  πŸ’»  πŸ…·  πŸ††  πŸ“¦  πŸ†  πŸ…Ό  πŸ…Ά  πŸ“Ό  πŸ›   9 https://kylrth.com/paper/google-nmt-2016/
2022-05-27 1:56PM Google's multilingual neural machine translation system ❢  πŸ“„  πŸ’»  πŸ…·  πŸ††  πŸ“¦  πŸ†  πŸ…Ό  πŸ…Ά  πŸ“Ό  πŸ›   9 https://kylrth.com/paper/google-zero-shot/
2022-05-27 1:56PM Forward and reverse gradient-based hyperparameter optimization ❢  πŸ“„  πŸ’»  πŸ…·  πŸ††  πŸ“¦  πŸ†  πŸ…Ό  πŸ…Ά  πŸ“Ό  πŸ›   10 https://kylrth.com/paper/gradient-based-hyperparameter-optimization/
2022-05-27 1:56PM papers on Kyle Roth ❢  πŸ“„  πŸ’»  πŸ…·  πŸ††  πŸ“¦  πŸ†  πŸ…Ό  πŸ…Ά  πŸ“Ό  πŸ›   8 https://kylrth.com/paper/index.xml
2022-05-27 1:56PM Inductive biases for deep learning of higher-level cognition ❢  πŸ“„  πŸ’»  πŸ…·  πŸ††  πŸ“¦  πŸ†  πŸ…Ό  πŸ…Ά  πŸ“Ό  πŸ›   9 https://kylrth.com/paper/inductive-biases-higher-cognition/
2022-05-27 1:56PM Learning explanations that are hard to vary ❢  πŸ“„  πŸ’»  πŸ…·  πŸ††  πŸ“¦  πŸ†  πŸ…Ό  πŸ…Ά  πŸ“Ό  πŸ›   10 https://kylrth.com/paper/learning-explanations-hard-to-vary/
2022-05-27 1:56PM kylrth.com/paper/learning-explanations-hard-to-vary/example.png ❢  πŸ“„  πŸ’»  πŸ…·  πŸ††  πŸ“¦  πŸ†  πŸ…Ό  πŸ…Ά  πŸ“Ό  πŸ›   4 https://kylrth.com/paper/learning-explanations-hard-to-vary/example.png
2022-05-27 1:56PM kylrth.com/paper/learning-explanations-hard-to-vary/figure6.png ❢  πŸ“„  πŸ’»  πŸ…·  πŸ††  πŸ“¦  πŸ†  πŸ…Ό  πŸ…Ά  πŸ“Ό  πŸ›   4 https://kylrth.com/paper/learning-explanations-hard-to-vary/figure6.png
2022-05-27 1:56PM kylrth.com/paper/learning-explanations-hard-to-vary/figure8.png ❢  πŸ“„  πŸ’»  πŸ…·  πŸ††  πŸ“¦  πŸ†  πŸ…Ό  πŸ…Ά  πŸ“Ό  πŸ›   4 https://kylrth.com/paper/learning-explanations-hard-to-vary/figure8.png
2022-05-27 1:56PM Masked autoencoders are scalable vision learners ❢  πŸ“„  πŸ’»  πŸ…·  πŸ††  πŸ“¦  πŸ†  πŸ…Ό  πŸ…Ά  πŸ“Ό  πŸ›   9 https://kylrth.com/paper/masked-autoencoders-are-scalable-vision-learners/
2022-05-27 1:56PM A meta-transfer objective for learning to disentangle causal mechanisms ❢  πŸ“„  πŸ’»  πŸ…·  πŸ††  πŸ“¦  πŸ†  πŸ…Ό  πŸ…Ά  πŸ“Ό  πŸ›   9 https://kylrth.com/paper/meta-transfer-objective-for-causal-mechanisms/
2022-05-27 1:56PM Towards a multi-view language representation ❢  πŸ“„  πŸ’»  πŸ…·  πŸ††  πŸ“¦  πŸ†  πŸ…Ό  πŸ…Ά  πŸ“Ό  πŸ›   10 https://kylrth.com/paper/multi-view-language-representation/
2022-05-27 1:56PM Learning neural causal models from unknown interventions ❢  πŸ“„  πŸ’»  πŸ…·  πŸ††  πŸ“¦  πŸ†  πŸ…Ό  πŸ…Ά  πŸ“Ό  πŸ›   9 https://kylrth.com/paper/neural-causal-models/
2022-05-27 1:56PM Neural message passing for quantum chemistry ❢  πŸ“„  πŸ’»  πŸ…·  πŸ††  πŸ“¦  πŸ†  πŸ…Ό  πŸ…Ά  πŸ“Ό  πŸ›   9 https://kylrth.com/paper/neural-message-passing/
2022-05-27 1:56PM It's not just size that matters: small language models are also few-shot learners ❢  πŸ“„  πŸ’»  πŸ…·  πŸ††  πŸ“¦  πŸ†  πŸ…Ό  πŸ…Ά  πŸ“Ό  πŸ›   9 https://kylrth.com/paper/not-just-size-that-matters/
2022-05-27 1:56PM Overcoming catastrophic forgetting in neural networks ❢  πŸ“„  πŸ’»  πŸ…·  πŸ††  πŸ“¦  πŸ†  πŸ…Ό  πŸ…Ά  πŸ“Ό  πŸ›   10 https://kylrth.com/paper/overcoming-catastrophic-forgetting/
2022-05-27 1:56PM papers ❢  πŸ“„  πŸ’»  πŸ…·  πŸ††  πŸ“¦  πŸ†  πŸ…Ό  πŸ…Ά  πŸ“Ό  πŸ›   9 https://kylrth.com/paper/page/2/
2022-05-27 1:56PM papers ❢  πŸ“„  πŸ’»  πŸ…·  πŸ††  πŸ“¦  πŸ†  πŸ…Ό  πŸ…Ά  πŸ“Ό  πŸ›   9 https://kylrth.com/paper/page/3/
2022-05-27 1:56PM papers ❢  πŸ“„  πŸ’»  πŸ…·  πŸ††  πŸ“¦  πŸ†  πŸ…Ό  πŸ…Ά  πŸ“Ό  πŸ›   9 https://kylrth.com/paper/page/4/
2022-05-27 1:56PM papers ❢  πŸ“„  πŸ’»  πŸ…·  πŸ††  πŸ“¦  πŸ†  πŸ…Ό  πŸ…Ά  πŸ“Ό  πŸ›   9 https://kylrth.com/paper/page/5/
2022-05-27 1:56PM papers ❢  πŸ“„  πŸ’»  πŸ…·  πŸ††  πŸ“¦  πŸ†  πŸ…Ό  πŸ…Ά  πŸ“Ό  πŸ›   9 https://kylrth.com/paper/page/6/
2022-05-27 1:56PM papers ❢  πŸ“„  πŸ’»  πŸ…·  πŸ††  πŸ“¦  πŸ†  πŸ…Ό  πŸ…Ά  πŸ“Ό  πŸ›   10 https://kylrth.com/paper/page/7/
2022-05-27 1:56PM papers ❢  πŸ“„  πŸ’»  πŸ…·  πŸ††  πŸ“¦  πŸ†  πŸ…Ό  πŸ…Ά  πŸ“Ό  πŸ›   9 https://kylrth.com/paper/page/8/

Showing 281-320 of 590 total
« first   previous   Page 8 of 15   next   last »