One-Shot Learning in Discriminative Neural Networks — HN submission

Wed, 29 Jul 2020 14:57:53 GMT

Launch HN: Humanloop (YC S20) – A platform to annotate, train and deploy NLP

Hey HN. We’re Peter, Raza and Jordan of Humanloop (https://humanloop.com) and we’re building a low code platform to annotate data, rapidly train and then deploy Natural Language Processing (NLP) models. We use active learning research to make this possible with 5-10x less labelled data. We’ve worked on large machine learning products in industry (Alexa, text-to-speech systems at Google and in insurance modelling) and seen first-hand the huge efforts required to get these systems trained, deployed and working well in production. Despite huge progress in pretrained models (BERT, GPT-3), one of…

157 points; 33 discussion replies on HN. Paper and source history. A submission is not an endorsement.

One-Shot Learning in Discriminative Neural Networks · HackerPapers discussions

One-Shot Learning in Discriminative Neural Networks — HN submission