https://hackerpaper.kaipfister.de/p/1802.07535/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=17588451urn:hackerpapers:mention:1802.07535:17588451Sun, 22 Jul 2018 19:33:49 GMT<p>It&#x27;s the opposite, they are very data efficient (compared to neural networks). Also, they are a bayesian method and give some mathematical guarantees. They are computationally expensive though. You can use them in neural nets to do few shot learning [0]. [0] https://arxiv.org/pdf/1802.07535.pdf or https://arxiv.org/abs/1807.01622</p><p><a href="https://hackerpaper.kaipfister.de/p/1802.07535/">Paper and discussion history</a>. A mention is not an endorsement.</p>stat.ML