11–20 of 137 posts
Earlier quoted context omitted.
Thanks for the feedback — added context to that sentence to make it more clear! The main interesting thing is that none of the Amazon data was labeled, while the 232 labeled examples were.
To further clarify: does unlabeled mean "we didn't use sentiment data" or "we were only trying to predict the next character given the prior characters", since the amazon data does come with associated 1-5 star ratings, were those used or not?
Earlier quoted context omitted.
To further clarify: does unlabeled mean "we didn't use sentiment data" or "we were only trying to predict the next character given the prior characters", since the amazon data does come with associated 1-5 star ratings, were those used or not?
We did not use the star ratings.
I don't know, but this seems a bit hyped in places. They start with: > Our L1-regularized model matches multichannel CNN performance with only 11 labeled examples, and state-of-the-art CT-LSTM Ensembles with 232 examples. Hmm, that sounds pretty impressive. But then later you read: > We first trained a multiplicative LSTM with 4,096 units on a corpus of 82 million Amazon reviews to predict the next character in a chu…
The synthetic text they generated was surprisingly realistic, despite being generic. If I were perusing a dozen reviews I probably wouldn't have spotted the AI-generated ones in the crowd.
I don't know, but this seems a bit hyped in places. They start with: > Our L1-regularized model matches multichannel CNN performance with only 11 labeled examples, and state-of-the-art CT-LSTM Ensembles with 232 examples. Hmm, that sounds pretty impressive. But then later you read: > We first trained a multiplicative LSTM with 4,096 units on a corpus of 82 million Amazon reviews to predict the next character in a chu…
I don't know, but this seems a bit hyped in places. They start with: > Our L1-regularized model matches multichannel CNN performance with only 11 labeled examples, and state-of-the-art CT-LSTM Ensembles with 232 examples. Hmm, that sounds pretty impressive. But then later you read: > We first trained a multiplicative LSTM with 4,096 units on a corpus of 82 million Amazon reviews to predict the next character in a chu…
Which, now that I think about it, makes the human brain and its amazing adaptive general-game-playing abilities a bit less mysterious. Since we humans all have these huge corpuses of sense-data we've been receiving reinforcement signals about since birth, we've likely built up all sorts of low-level models which we just use to predict the world for reflex responses a little bit better and faster (speech models so we can respond to what people are saying even as they're still saying it, visual models so we can throw spears where lions are going to be instead of where they are, etc.) But those low-level predictive models make it nearly effortless to build higher-level models.
I wonder if we'd take a giant leap forward in AI if we just managed to scan+emulate a regular animal brain (say, of a rat), and then built the AI as a neocortex-equivalent for that brain. It would have instant access to thousands or millions of pre-trained low-level predictive models, which it could easily discover as having outputs correlated to success and thus "attach to" during its own training.
The synthetic text they generated was surprisingly realistic, despite being generic. If I were perusing a dozen reviews I probably wouldn't have spotted the AI-generated ones in the crowd.
We are getting better and better with automatic text generation. I wonder who will be the copyright owner of an AI-generated text, comments, songs, etc.?
I don't know, but this seems a bit hyped in places. They start with: > Our L1-regularized model matches multichannel CNN performance with only 11 labeled examples, and state-of-the-art CT-LSTM Ensembles with 232 examples. Hmm, that sounds pretty impressive. But then later you read: > We first trained a multiplicative LSTM with 4,096 units on a corpus of 82 million Amazon reviews to predict the next character in a chu…
I think it's a fair claim. Labelled data is very hard to come by compared to unlabelled data. Being able to get a highly accurate model with only a small amount of labelled data is a very sought after and practical property.