Note Yoshua Bengio in the author list. This shouldn't be taken lightly.
Who cares. Look at Jeffrey Hinton right now. Do you trust him? :-D
Were RNNs all we needed?
111–120 of 269 posts
Re: Were RNNs all we needed?
#112It's curse and a blessing that discussion of topics happens in so many different places. I found this comment on Twitter/X interesting: https://x.com/fchollet/status/1841902521717293273 "Interesting work on reviving RNNs. https://arxiv.org/abs/2410.01201 -- in general the fact that there are many recent architectures coming from different directions that roughly match Transformers is proof that architectures aren't f…
Most LLMs aren't even using a "curve" yet at all, right? All they're using is a series of linear equations because the model weights are a simple multiply and add (i.e. basic NN Perceptron). Sure there's a squashing function on the output to keep it in a range from 0 to 1 but that's done BECAUSE we're just adding up stuff. I think probably future NNs will be maybe more adaptive than this perhaps where some Perceptron…
> It's astounding that we DID get the emergent intelligence from just doing this "curve fitting" onto "lines" rather than actual "curves".
In Ye Olden days (the 90’s) we used to approximate non-linear models using splines or seperate slopes models - fit by hand. They were still linear, but with the right choice of splines you could approximate a non-linear model to whatever degree of accuracy you wanted.
Neural networks “just” do this automatically, and faster.
Re: Were RNNs all we needed?
#113Earlier quoted context omitted.
> squash an output into a range This isn't the primary purpose of the activation function, and in fact it's not even necessary. For example see ReLU (probably the most common activation function), leaky ReLU, or for a sillier example: https://youtu.be/Ae9EKCyI1xU?si=KgjhMrOsFEVo2yCe
You can change the subject by bringing up as many different NN architectures, Activation Functions, etc. as you want. I'm telling you the basic NN Perceptron design (what everyone means when they refer to Perceptrons in general), has something like a `tanh` and not only is it's PRIMARY function to squash a number, that's it's ONLY function.
How was that person derailing the convo? Nothing says an activation function has to "squash" a number to be in some range. Leaky ReLUs for instance do `f(x) = x if x > 0 else ax` (for some coefficient `a != 0`), that doesn't squash `x` to be in any range (unless you want to be peculiar about your precise definition of what it means to squash a number). The function takes a real in `[-inf, inf]` and produces a number in `[-inf, inf]`.
> Sure there's a squashing function on the output to keep it in a range from 0 to 1 but that's done BECAUSE we're just adding up stuff.
It's not because you're "adding up stuff", there is specific mathematical or statistical reason why it is used. For neural networks it's there to stop your multi layer network collapsing to a single layer one (i.e. a linear algebra reason). You can choose whatever function you want, for hidden layers tanh generally isn't used anymore, it's usually some variant of a ReLU. In fact Leaky ReLUs are very commonly used so OP isn't changing the subject.
If you define a "perceptron" (`g(Wx+b)` and `W` is a `Px1` matrix) and train it as a logistic regression model then you want `g` to be sigmoid. Its purpose is to ensure that the output can be interpreted as a probability (given that use the correct statistical loss), which means squashing the number. The inverse isn't true, if I take random numbers from the internet and squash them to `[0,1]` I don't go call them probabilities.
> and not only is it's PRIMARY function to squash a number, that's it's ONLY function.
Squashing the number isn't the reason, it's the side effect. And even then, I just said that not all activation functions squash numbers.
> All the training does is adjust linear weights tho, like I said.
Not sure what your point is. What is a "linear weight"?
We call layers of the form `g(Wx+b)` "linear" layers but that's an abused term, if g() is non-linear then the output is not linear. Who cares if the inner term `Wx + b` is linear? With enough of these layers you can approximate fairly complicated functions. If you're arguing as to whether there is a better fundamental building block then that is another discussion.
Re: Were RNNs all we needed?
#114RNNs always had better scaling law curves than transformers.
BPTT was their problem
Re: Were RNNs all we needed?
#115Excited to see more people working on RNNs but wish their citations were better.
In 2016 my team from Salesforce Research published our work on the Quasi-Recurrent Neural Network[1] (QRNN). The QRNN variants we describe are near identical (minGRU) or highly similar (minLSTM) to the work here.
The QRNN was used, many years ago now, in the first version of Baidu's speech recognition system (Deep Voice [6]) and as part of Google's handwriting recognition system in Gboard[5] (2019).
Even if there are expressivity trade-offs when using parallelizable RNNs they've shown historically they can work well and are low resource and incredibly fast. Very few of the possibilities regarding distillation, hardware optimization, etc, have been explored.
Even if you need "exact" recall, various works have shown that even a single layer of attention with a parallelizable RNN can yield strong results. Distillation down to such a model is quite promising.
Other recent fast RNN variants such as the RWKV, S4, Mamba et al. include citations to QRNN (2016) and SRU (2017) for a richer history + better context.
The SRU work has also had additions in recent years (SRU++), doing well in speech recognition and LM tasks where they found similar speed benefits over Transformers.
I note this primarily as the more data points, especially when strongly relevant, the better positioned the research is. A number of the "new" findings from this paper have been previously explored - and do certainly show promise! This makes sure we're asking new questions with new insights (with all the benefit of additional research from ~8 years ago) versus missing the work from those earlier.
[1] QRNN paper: https://arxiv.org/abs/1611.01576
[2] SRU paper: https://arxiv.org/abs/1709.02755
[3]: SRU++ for speech recognition: https://arxiv.org/abs/2110.05571
[4]: SRU++ for language modeling: https://arxiv.org/abs/2102.12459
[5]: https://research.google/blog/rnn-based-handwriting-recogniti...
Re: Were RNNs all we needed?
#116Earlier quoted context omitted.
> squash an output into a range This isn't the primary purpose of the activation function, and in fact it's not even necessary. For example see ReLU (probably the most common activation function), leaky ReLU, or for a sillier example: https://youtu.be/Ae9EKCyI1xU?si=KgjhMrOsFEVo2yCe
You can change the subject by bringing up as many different NN architectures, Activation Functions, etc. as you want. I'm telling you the basic NN Perceptron design (what everyone means when they refer to Perceptrons in general), has something like a `tanh` and not only is it's PRIMARY function to squash a number, that's it's ONLY function.
You need a non-linear activation function for the universal approximation theorem to hold. Otherwise, as others have said the model just collapses to a single layer.
Technically the output is still what a statistician would call “linear in the parameters”, but due to the universal approximation theorem it can approximate any non-linear function.
https://stats.stackexchange.com/questions/275358/why-is-incr...
Re: Were RNNs all we needed?
#117Earlier quoted context omitted.
The non linearities are fundamental. Without them, any arbitrarily deep NN is equivalent to a shallow NN (easily computable, as GP was saying), and we know those can't even solve the XOR problem. > nothing but linearity No, if you have non linearities, the NN itself is not linear. The non linearities are not there primarily to keep the outputs in a given range, though that's important, too.
> The non linearities are not there primarily to keep the outputs in a given range Precisely what the `Activation Function` does is to squash an output into a range (normally below one, like tanh). That's the only non-linearity I'm aware of. What other non-linearities are there? All the training does is adjust linear weights tho, like I said. All the training is doing is adjusting the slopes of lines.
> That's the only non-linearity I'm aware of.
"only" is doing a lot work here because that non-linearity is enough to vastly expand the landscape of functions that an NN can approximate. If the NN was linear, you could greatly simplify the computational needs of the whole thing (as was implied by another commenter above) but you'd also not get a GPT out of it.
Re: Were RNNs all we needed?
#118Earlier quoted context omitted.
> Even if many types of architectures converge to the same loss over time, finding the one that converges the fastest is quite valuable given the cost of running GPU's at scale. This! Not just fastest but with the lowest resources in total. Fully connected neural networks are universal functions. Technically we don’t need anything but a FNN, but memory requirements and speed would be abysmal far beyond the realm of p…
Unless we could build chips in 3D?
Heat extraction.
Re: Were RNNs all we needed?
#119Re: Were RNNs all we needed?
#120It's curse and a blessing that discussion of topics happens in so many different places. I found this comment on Twitter/X interesting: https://x.com/fchollet/status/1841902521717293273 "Interesting work on reviving RNNs. https://arxiv.org/abs/2410.01201 -- in general the fact that there are many recent architectures coming from different directions that roughly match Transformers is proof that architectures aren't f…
Well, you also need an approach to 'curve fitting' where it's actually computationally feasible to fit the curve. The approach of mixing layers of matrix multiplication with a simple non-linearity like max(0, x) (ReLU) works really well for that. Earlier on they tried more complicated non-linearities, like sigmoids, or you could try an arbitrary curve that's not split into layers at all, you would probably find it harder. (But I'm fairly sure in the end you might end up in the same place, just after lots more computation spent on fitting.)