This actually demonstrates something very interesting, I think: you can take an ML model trained with the "low-level prerequisite knowledge" of a subject, and then very quickly and easily teach it a high-level concept that relies on that knowledge.

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.

What you describe is exactly what practitioners in the field have been doing for years. I think that's why the parent is a bit puzzled at the publication, as it's difficult to understand what's novel.

Yes, I agree with you but with a caveat. Semi-supervised learning is well known but has, I'll argue, recently fallen out of fashion in favor of throwing gallons more of labeled data at a really big neural net, crossing your fingers and hoping for the best. Usually, the neural net is either a really big conv-net with a novel architecture or a biLSTM with some elaboration on attention (which is actually closer to memory/state).

Most of the time, in neural net land, what people are doing with the fine tuning part is taking a model trained on looaads of supervised data, chopping off the head and using those features to train on smaller data. This OpenAI method is different in that it used patterns it learned on its own, instead of the recently more common technique of features extracted from a heavily label trained model to reduce the supervised learning burden in a nearby domain.

Arguably yes, this is an ancient technique but it has mostly been forgotten when it became clear that many problems are surmountable with a large enough helping of GPUs and a small moon's worth of data. OpenAI's is a good idea because it makes you say 'yeah that's obvious, pretrain a simple char rnn on loads of free text and oh wait, why has no one tried this before!?'

What is interesting here is that such a straight forward method compares so well to glittering methods that laboriously advanced the state of the art. What I also found surprising was that there was a 'neuron' that was tracking something very close to sentiment. Why?

A bit of thinking and I came to a simple idea. One way of looking at the LSTM in the practical setting (as opposed to a theoretically Turing Equivalent thing) is as a really big finite state rube goldberg machine. In learning to predict the next character, it makes sense that one set or part of a set of states it can enter/track is extremely correlated with what we humans call sentiment in review text.

In summary, the trained model can be thought of as a computable theory of amazon reviews that also works really well on IMDB reviews (and probably short but probably not sarcastic text reviews in general).

thanks for clarifying this- it isn't transfer learning at all, more like the techniques like, digging through LSTMs post hoc to find the neuron responsible for opening and closing quotation marks (insert karpathy youtube vid here), except for a more "high level" feature - in this case, sentiment.

Indeed, although I'm not as familiar with transfers this far (that is, fine-tuning models is really common with image recognition tasks, but often you take a model trained to recognize objects in images, and train it to recognize different objects in images, but you're still recognizing objects in images).

This feels a bit different, in that yesterday I would have had no strong intuition that "a char-rnn can detect text sentiment better than sota". Looking now, I can rationalize that idea. I get why it might make sense, but it was non-obvious. Do you disagree with any of that? (and if you do, I'd love to see this distance of transfer in literature, its always cool to read up on these things)

Practitioners have been doing this for vision, and transfer learning is not very popular in language. This work is the first that I have heard of that uses transfer learning for language.

What you are proposing with the rat brain simulation/scan seems pretty close to what the Blue Brain Project folks are doing: http://bluebrain.epfl.ch/page-56882-en.html

Would that be why people raised in dysfunctional or abusive families have very deep rooted issues? Everything learned later in life seems more fluid, but some of those problematic attitudes or personality traits are extremely hard to change. Seems consistent with those parts being build in lower layers with a decades long training experience. And yet at a higher level things can be learned and changed fairly easily.

This is essentially linear algebra, not behavioural psychology. I believe that one shouldn't draw such broad conclusions from a 1% improvement on some evaluation dataset.

I'm glad we're not tolerating attempts at pretending deep learning has anything to do with brains.

I was talking about the ability to use thin layers over top of broad learning. If neural networks are a realistic analogy at all, I think it fits. The roots of all this ML stuff is not straight from linear algebra even though much of the math is.

You're playing it extremely fast and loose with concepts like "low-level prerequisite knowledge" and how exactly does something "rel[y] on that knowledge", though. These aren't physical quantities like temperature where we -- as a species -- have the massive amount of low-level prerequisite knowledge that allows us to make rapid high level judgments that rely on that knowledge. The previous sentence is an example of how easy this reasoning is to abuse.

Could be possible. For example, when a child is deprived of any human and humane contact, they end up with a very very impoverished linguistic system as well as delayed development of all cognitive abilities. Could be because the lack the unsupervised training phase.

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.

The technique of training a model on a lot of data for a long time and then leveraging its sophisticated representation only learning the last layer(s) on small datasets to create accurate models is common practice.

Beating the state-of-the-art with one-shot learning is not common. Transfer learning for NLP is also quite unchartered.

Also the technique is quite novel: This is not pre-trained nets on labeled data, it is an unsupervised generative model.

Future research directions are exciting: Unsupervised prediction of the next frame in a video, and then being able to one-shot learn a wide range of visual tasks.

You might be interested in minute 50 onward [0], or this recent paper from Facebook [1].

[0] https://www.youtube.com/watch?v=-yX1SYeDHbg&list=PLE6Wd9FR--...

[1] https://arxiv.org/abs/1703.07684

Cool. I knew of previous work [1], but not the recent paper you posted. Thanks.

[1] https://arxiv.org/abs/1412.6056 "Predicting Deeper into the Future of Semantic Segmentation"

It's a good idea, but it doesn't seem very common so far.

This is what my NLP company (Luminoso) does -- we train a domain-general model of word meanings on a lot of data, then do the last step on the probably-small amount of specific data you actually have.

Even customers who are knowledgeable about machine learning usually haven't heard of the idea before. They've been assuming that the only way to do NLP is to get millions of labeled examples. Or to get a thousand labeled examples and put them into the kind of off-the-shelf algorithm that needs millions of labeled examples, which of course goes poorly.

My ML background is primarily undergraduate work, and even then it was extremely common.

It's not as easy as what you just described, especially on sequential data. Sure, people already use embeddings built by different models for different tasks (think word2vec, last layer from inception, etc.) but this rarely performs as well as what this article shows.

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.

Very interesting, this reminds me of the 2012 paper by Andrew Ng: Building High-level Features Using Large Scale Unsupervised Learning

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.

Have you looked at cross referencing against the star ratings? Would be interesting to see how predictive this was of those ratings... or even if another variable in the system could predict that?

That's what I thought, and that makes this all the more interesting!

isn't it impressive? They trained a network to predict the next character and when the finished they trained the last layer to predict sentiment with only few examples. The network was able to learn sentiment somehow in the first training phase without telling it!

For me this open my mind to new opportunities when training deep learning. For example I can do the same for images: train a network to recognize objects and later use the same network to predict sentiment or prettiness for example. And the best thing is that I don't need a lot of labeled examples for the second phase of training!

Immediate thought - the network didn't learn sentiment in the training phase, it just clustered the data. The last phase was so quick to train because it was labeling already-clustered data, so a few data points in each cluster was enough to make it 'obvious'.

Actually it was only an output neuron, and for me it is the same if you call it cluster or not. It just learnt sentiment without any hint. Now I wonder if they can train it again and get the same sentiment neuron, that would mean something. Like sentiment is necessary to predict the next character? (word?)

It's essentially the nlp equivalent transfer learning from the computer vision side.

No this is quite a bit different. In transfer learning in computer vision, people are using a network trained on another, typically large dataset, and using the learned features on a different data set.

This LSTM simply learned to predict the data. It didn't learn some other supervised task.

This would be more similar to autoencoder pretraining, but even that is not quite the same.

Is this correct? My sense from the article is that they did all the training on unsupervised, and then checked one of the recurrent lines for a correlation to sentiment, not adding a layer and doing more training.

They can - because the examples weren't labelled. In principle, you could use the model to train a whole lot of other things (what age group does a product appeal to? Is this product targeted at men/women?) with just a few hundred examples.

With 82 million examples it learned how to spell each word and which word follows which in a sentence.

With the 232 examples it learned What bad sentiment sentences look like and which words occur in them.