Slashdot Mirror
Google Brain's Co-inventor Tells Why He's Building Chinese Neural Networks
An anonymous reader writes "Here's an interview with Andrew Ng, former leader of Google Brain, discussing Baidu, Deep Learning, computer neural networks, and AI. An interesting excerpt from the interview on biological vs. computer neural networks: "A single 'neuron' in a neural network is an incredibly simple mathematical function that captures a minuscule fraction of the complexity of a biological neuron. So to say neural networks mimic the brain, that is true at the level of loose inspiration, but really artificial neural networks are nothing like what the biological brain does."
Make a hole with a gun perpendicular
To the name of this town in a desk-top globe
Exit wound in a foreign nation
Showing the home of the one this was written for
My apartment looks upside down from there
Water spirals the wrong way out the sink
And her voice is a backwards record
It's like a whirlpool and it never ends
Andrew Ng and I are getting old
And we still haven't walked in the glow of each other's majestic presence
Listen Andrew hear my words
They're the ones you would think I would say if there was a me for you
All alone at the '64 World's Fair
Eighty dolls yelling "Small man after all"
Who was at the Dupont Pavilion?
Why was the bench still warm? Who had been there?
Or the time when the storm tangled up the wire
Having crossed paths with this fella about 10 years ago, you're not too far off. Minus the racism.
artificial neural networks are nothing like what the biological brain does.
... there are quite a few people around who tried to overclock their brains during the '60s and '70s.
Have gnu, will travel.
It is Controller, is it not?
UGH! Why can't I edit comments like every other message board on the face of the Earth!?!?
To say that "artificial neural networks are nothing like what the biological brain does" is no more correct than to say "artificial neural networks are just like the brain."
Machine learning neural networks do the same flavor of thing that a real organic brain does, but at a complexity that is -many- orders of magnitude smaller. They also tend to be directed at a single skill, and don't have to cohabit the network with, well, everything.
They're not the same, but they're not totally different, either. Truth is not well served by hyperbole.
Don't take life too seriously; it isn't permanent.
An hour after you turn them one they are hungry for singularity.
Certainly biological neurons are much more complex than artificial neural net neurons. The simplest "Integrate and Fire" (IF) model of a biological neuron perform a leaky integration over *time*, and if the voltage ever reaches the trigger value the fire. So the timing of stimulations is critical, whereas most Artificial Neural Networks (ANNs) does all its calculations (logically) at the same time. The ANN is both simpler and cleaner to work with. Biological synapses are very complex, but much of that complexity just reflects the wet technology that they are made from.
If you want to understand how the brain works, study biological neurons. If you want to understand how to build an intelligent machine, engineer ANNs.
That is NOT what a Chinese Room is!
Having crossed paths with this fella about 10 years ago, you're not too far off. Minus the racism.
I did not realize that Chinese was a race. I thought it was a nationality. Is this like how people who question Islam are called racists? Islam is also not a race but a religion and potentially an ideology. Should people oppose communism be called racists too?
Jesus was a compassionate social conservative who called individuals to sin no more.
From the TFA:
What about words that donâ(TM)t exist in one language versus another?
How come the word Butter doesn't mean more butt?
Chinese-as-race is probably referring to the Han Chinese ethnicity.
He's just doing what everyone else who succeeds in this business does. Downloading libraries to recreate popular results and doing better demos. You might as well accuse 90% of PhD students of doing the same thing. In fairness, you probably are.
Man, we get jaded in this business, don't we?
Well you're wrong. My family is from Taiwan, but identify racially as Chinese.
Actually, most of them are nonlinear. Sigmoid function is common, and there are much more exotic things going on too, such as fuzzy logic-based discriminants. Bottom line is that any discriminatory function is of interest.
There's also some fascinating stuff going on with time discriminants where they're having very encouraging results.
Odds are excellent that both (time and transfer function) are part of a solution that is most human-neuron-like. But it isn't by any means a given that we have to go there to make actual AI work. That's just how we work. Also, I am fairly confident, like this.
I've fallen off your lawn, and I can't get up.
In addition to very high complexity, fixed topology (meaning, using primarily electrical, chemical and timing means as opposed to topological modification to operate), general problem solving networks, I am fairly confident that we develop plenty of what can accurately be described as single-skill networks, topologically tuned to individual problems by continuous cut-and-fit until the errors drop. I lay out why right here.
I've fallen off your lawn, and I can't get up.
He gets paid to do it. Typical Chinese.
Because this is slashdot and we don't like posts that aren't well thought out and cohesive. Read before you hit that button. You'll thank me for that advice after someone rips you a new asshole on here because what you wrote looks like it was written by a 5 year old.
https://en.wikipedia.org/wiki/...
That's because you don't know what a race is. Go read about the definition (Wikipedia is a good start) and let it sink in.