Hacker Read top | best | new | newcomments | leaders | about | bookmarklet login

> The neural engine is small and inference only

Why is it inference only? At least the operations are the same...just a bunch of linear algebra



sort by: page size:

> it’s the maths for neural networks largely multiplying large arrays/tensors together?

Yes, it's multiplying and adding matrices. That and mapping some simple function over an array.

Neural networks are only that.


> Am I wrong to think that most modern machine learning models are simply about sophisticated pattern recognition and statistical inference?

You aren't wrong. Modern Machine learning is entirely statistical inference, mostly through minimizing an objective function.

> Wouldn't this have a limit on functionality?

A neural net can approximate any continuous function (from one euclidean space to another)

https://en.wikipedia.org/wiki/Universal_approximation_theore...


> as I scientist I am very uninterested in AI based on neural nets because of the lack of explication

Neural nets are more like reflexes than reasoning. Most of them are feed forward and some don't even have memory and can't solve references. So it's unfair to expect a job that is best done based on graphs or on memory-attention to be done by a rudimentary system that only knows to map X to y.

But they are not totally unexplainable - you can get gradients on the data and see what parts of the input data most influenced the output, then you can perturb the inputs to see how the output would change.


> What so-called neural networks do should not be confused with thinking, at least not yet.

I disagree:

I think neural networks are learning an internal language in which they reason about decisions, based on the data they’ve seen.

I think tensor DAGs correspond to an implicit model for some language, and we just lack the tools to extract that. We can translate reasoning in a type theory into a tensor DAG, so I’m not sure why people object to that mapping working the other direction as well.


> Machine learning is linear algebra, nothing more nothing less

Neural nets are non-linear. If they were linear, that would be linear regression.

I actually don't get what your point is.


> The only numerical linear algebra related to machine learning, in particular deep learning, is matrix multiplication

I suspect the OP is not talking about how deep nets are implemented, but rather how people are trying to understand how and why they work so well, or how to reverse-engineer knowledge out of a trained net, or how to train them faster, etc ...

In that space, you need quite a bit more than matrix multiplication.


> It’s clear transformers can’t understand either case. They’re not architecturally designed to.

What does this follow from?

> The emergent behavior of appearing to do so is only driven by how much data you throw at them.

This is true for almost every neural network, no?


> it's nothing more than a ultra-scaled neural network as we currently use them

You state this as if it is an undisputed/obvious fact, but it isn't.


> The truth is that even the experts don’t completely understand how neural nets work.

I'm no AI/ML expert, but I can't believe this is true... Is it?


> The truth is that even the experts don’t completely understand how neural nets work.

That is not understanding.


>some neural nets and others not.

Source for the brain having computational units that aren't neural nets? I'd love to read more on this.


Quote:

The purpose of this article is to give programmers without much exposure to machine learning an understanding of the key building block powering generative AI: the artificial neuron.

Toward that end, this article has three goals:

1. to implement a perceptron – the simplest artificial neuron;

2. to train perceptrons how to mimic AND, OR and NOT; and

3. to describe the leap to full-fledged neural networks.

(edit: formatting)


> artificial neural networks aren't like actual neural networks or brains

Just to zoom right in on neural networks:

People often say this, and I never see a solid argument.

I know very little about biological neural networks.

Clearly they are very different in some respects, for example, meat vs silicon.

But I never see a good argument that there's no perspective from which the computational structure is similar.

Yes, the low level structure, and the optimization is different, but so? You can run quicksort on a computer made of water and wood, or vaccum tubes, or transistors, and it's still quicksort.

Are we sure there aren't similarities in terms of how the various neural networks process information? I would be interested in argument for this claim.

After all, the artificial neural networks are achieving useful high level functionality, like recognizing shapes.


> There is no matrix math with neurons

Are we talking about the brain or neural nets biological plausible neural nets?


> I must have missed the part when it started doing anything algorithmically. I thought it’s applied statistics, with all the consequences of that.

This is a common misunderstanding. Transformers are actually Turing complete:

* On the Turing Completeness of Modern Neural Network Architectures, https://arxiv.org/abs/1901.03429

* On the Computational Power of Transformers and its Implications in Sequence Modeling, https://arxiv.org/abs/2006.09286


> You can just take connection and activation weights and write a simple neural network equivalent in an evening. And it would work about as good as a hardware simulation.

And yet, nobody has managed to do so, despite years of effort.

Why?


> If predictive coding and backpropagation are shown to have similar power, then there's a rough idea that the way that ANNs work isn't too far from how brains work (with lots and lots of caveats).

So many caveats that I don't even really think that is a true statement.


> We know precisely how any given neural network works, it's just not understandable to us.

You can't know something if it isn't understandable. Knowledge requires some sort of understanding.


> This is why I want any ML device to be able to explain itself.

This is the problem of lacking explanatory mechanisms in ML.

Note that some techniques that are very out of vogue at the moment, such as Genetic Programming, are much better than neural nets in this regard.

next

Legal | privacy