Pinboard (jm)
https://pinboard.in/u:jm/public/
recent bookmarks from jm[1907.06902] _Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approaches_2019-07-22T09:30:37+00:00
https://arxiv.org/abs/1907.06902
jmDeep learning techniques have become the method of choice for researchers working on algorithmic aspects of recommender systems. With the strongly increased interest in machine learning in general, it has, as a result, become difficult to keep track of what represents the state-of-the-art at the moment, e.g., for top-n recommendation tasks. At the same time, several recent publications point out problems in today's research practice in applied machine learning, e.g., in terms of the reproducibility of the results or the choice of the baselines when proposing new models. In this work, we report the results of a systematic analysis of algorithmic proposals for top-n recommendation tasks. Specifically, we considered 18 algorithms that were presented at top-level research conferences in the last years. Only 7 of them could be reproduced with reasonable effort. For these methods, it however turned out that 6 of them can often be outperformed with comparably simple heuristic methods, e.g., based on nearest-neighbor or graph-based techniques. The remaining one clearly outperformed the baselines but did not consistently outperform a well-tuned non-neural linear ranking method. Overall, our work sheds light on a number of potential problems in today's machine learning scholarship and calls for improved scientific practices in this area.
(via Halvar Flake)]]>via:halvarflake deep-learning machine-learning ml papers algorithms top-n heuristicshttps://pinboard.in/https://pinboard.in/u:jm/b:2df4ff4d47fb/Deep learning can "discover" new knowledge from scans/images2018-11-19T11:53:02+00:00
https://www.nature.com/articles/s41551-018-0195-0
jmHere, we show that deep learning can extract new knowledge from retinal fundus images. Using deep-learning models trained on data from 284,335 patients and validated on two independent datasets of 12,026 and 999 patients, we predicted cardiovascular risk factors not previously thought to be present or quantifiable in retinal images, such as age (mean absolute error within 3.26 years), gender (area under the receiver operating characteristic curve (AUC) = 0.97), smoking status (AUC = 0.71), systolic blood pressure (mean absolute error within 11.23 mmHg) and major adverse cardiac events (AUC = 0.70). We also show that the trained deep-learning models used anatomical features, such as the optic disc or blood vessels, to generate each prediction.
]]>deep-learning data analysis ml machine-learning health medicine papershttps://pinboard.in/https://pinboard.in/u:jm/b:59bb846c56f1/When DNNs go wrong – adversarial examples and what we can learn from them2017-02-28T16:56:25+00:00
https://blog.acolyer.org/2017/02/28/when-dnns-go-wrong-adversarial-examples-and-what-we-can-learn-from-them/
jm[The] results suggest that classifiers based on modern machine learning techniques, even those that obtain excellent performance on the test set, are not learning the true underlying concepts that determine the correct output label. Instead, these algorithms have built a Potemkin village that works well on naturally occuring data, but is exposed as a fake when one visits points in space that do not have high probability in the data distribution.
]]>ai deep-learning dnns neural-networks adversarial-classification classification classifiers machine-learning papershttps://pinboard.in/https://pinboard.in/u:jm/b:42c47bb5da43/