Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Evolution Is the New Deep Learning

sentient.ai

Post reply on HN
Print view View original

161–170 of 242 posts

Re: Evolution Is the New Deep Learning

#161

Post by Houshalter »

vanderZwan wrote: post #153
Houshalter wrote: post #149

Earlier quoted context omitted.

Evolvability can also evolve away too. For instance, a gene that decreases the mutation rate to 0. Most mutations are harmful, so any organism with the gene will be more likely to have successful children. And eventually the gene will become dominant and there will be no more mutations. And evolution will stop.

What you say is fairly hypothetical, since the way genetics works at a fundamental level prevents this possibility. You are also oversimplifying by not distinguishing local and global success. Locally, this gene will be successful. Globally, some mutations will be beneficial , and the children with those mutations will be more successful. The gene may become "dominant" (and then gain the beneficial mutations through…

It's not hypothetical. We haven't observed it in nature because any organism that evolved this would simply go extinct. But similar "evolving to extinction" phenomenons have been observed. Such as genes in mice that make the entire population male, or transposons in plants: http://lesswrong.com/lw/l5/evolving_to_extinction/

>it will not achieve a monopoly and not remove the existence of evolution.

Yes it will. It's easy to do simulations. Statistically the children of the organism with less mutations will have an advantage. Eventually the gene will reach 100% of the population. The population will stop evolving and eventually go extinct.

Re: Evolution Is the New Deep Learning

#162

Post by resource0x »

pas wrote: post #73
resu_nimda wrote: post #64

Earlier quoted context omitted.

1) One of the biggest reasons they fell out of favor for more "mathematical" approaches was that no one could really explain why exactly they worked. Kind of like how nobody can really explain how the brain works, or life in general. My gut feeling is that it is hubris to think that we are going to "figure out" intelligence with increasingly sophisticated mathematical models anytime soon. We are not giving proper cre…

> We are not giving proper credit to how complex it is, and the multi-billion year developmental process that it took. Or we are simply not ready to accept that it's simply a big book of heuristics fine-tuned over biological eons. It's just big. We have too many interwoven, interdependent, synergistic faculties. Input, output, and a lot of mental stuff for making the right connections between the ins and the outs. Th…

200 years ago there was nothing to understand in electricity: it was just a liquid :) https://en.wikipedia.org/wiki/Fluid_theory_of_electricity

Re: Evolution Is the New Deep Learning

#163

Post by padthai »

ozy wrote: post #117
padthai wrote: post #83

Earlier quoted context omitted.

There is plenty of magic going on. Today we cannot replicate or understand how emergent properties born of biological structures. Not even in "simple" systems as the metabolic pathways.

Same way waves emerge in water. The rules that govern a system can create patterns, which themselves behave according to rules, but with a set of rules that was "hard to predict" from the underlying system.

That is exactly my point. We can use fluid dynamics and PDEs in waves. We understand some properties and processes. We are nowhere as close in biological system.

I put the example of the metabolic pathways because last time checked (~2015) the most advanced things in the field were extremely simple and without any predictive power. Things like calculating the kernel of a stoichiometric matrix or the centrality of a node in the interactomic graph.

Re: Evolution Is the New Deep Learning

#164

Post by hueving »

dorgo wrote: post #120
resu_nimda wrote: post #64

Earlier quoted context omitted.

1) One of the biggest reasons they fell out of favor for more "mathematical" approaches was that no one could really explain why exactly they worked. Kind of like how nobody can really explain how the brain works, or life in general. My gut feeling is that it is hubris to think that we are going to "figure out" intelligence with increasingly sophisticated mathematical models anytime soon. We are not giving proper cre…

> My gut feeling is that it is hubris to think that we are going to "figure out" intelligence with increasingly sophisticated mathematical models anytime soon. We did it already. Compter understand language, translate it, react to it. They can recognize items on a picture. Is there a task left which can't be done by computers better and faster than by humans? >Almost by definition, if we can analytically understand i…

Yep, we're definitely done: http://rocknrollnerd.github.io/ml/2015/05/27/leopard-sofa.ht...

Re: Evolution Is the New Deep Learning

#165

Post by mrfusion »

pas wrote: post #73
resu_nimda wrote: post #64

Earlier quoted context omitted.

1) One of the biggest reasons they fell out of favor for more "mathematical" approaches was that no one could really explain why exactly they worked. Kind of like how nobody can really explain how the brain works, or life in general. My gut feeling is that it is hubris to think that we are going to "figure out" intelligence with increasingly sophisticated mathematical models anytime soon. We are not giving proper cre…

> We are not giving proper credit to how complex it is, and the multi-billion year developmental process that it took. Or we are simply not ready to accept that it's simply a big book of heuristics fine-tuned over biological eons. It's just big. We have too many interwoven, interdependent, synergistic faculties. Input, output, and a lot of mental stuff for making the right connections between the ins and the outs. Th…

Keep in mind the genome really isn’t big enough to store enough hueristics to make a functioning human.

Re: Evolution Is the New Deep Learning

#167

Post by netheril96 »

xants wrote: post #31
yorwba wrote: post #29

Earlier quoted context omitted.

If you mutate genomes by small additive modifications to a vector of continuous parameters, then taking lots of samples and keeping the best is essentially a stochastic approximation to gradient descent. However, unlike the SGD used in deep learning, it doesn't make use of calculus and therefore requires many more samples (exponentially more, in the worst case) to get a gradient of equivalent accuracy. I.e. it's slow…

Is it true that genetic algorithms have the benefit of being able to find the global optima more consistently due to the incorporation of randomness in subsequent generations? Whereas DL models often get stuck at local optima?

Deep learning has enough randomness. The random weight initialization, the random choice of samples (as in name Stochastic Gradient Descent), the random flip/crop/noise in data augmentation, and randomness injected by dropout.

Re: Evolution Is the New Deep Learning

#168

Post by oldandtired »

ahartmetz wrote: post #115
pas wrote: post #95

Earlier quoted context omitted.

I'm assuming a simpler model, no need for magic, because so far I don't see what behavior/data this simple model cannot explain. > Clearly it's not that simple or easy, or we would have done it. We don't have the computational power yet. Not to mention the vast amount of development required. Think of the climate models, that are huge (millions of lines of code), but they're still nowhere near complete enough, and th…

We don't fully understand life. We don't even understand all the proteins. We sure don't understand a single neuron. We understand many small and big things about life, yes.

In part I agree with you. The big difference is that we don't understand the fundamental difference between what is alive and what isn't. We have many different ideas about the quality that is called "life" or living. We have no clue about what it is.

We have little or no understanding of the complex protocols that occur within a cell. If we did, our standard manufacturing techniques would be vastly different.

We can modify DNA and RNA in interesting ways, but they are not living. It is not until we put them into an already existing living cell that we can reprogram some characteristics of that cell.

Re: Evolution Is the New Deep Learning

#169

Post by Jack000 »

yters wrote: post #166

If evolutionary algorithms are so magical, why do I only encounter them in academia?

they're slow and if you had even an approximate analytical solution, you'd use that instead.

evolutionary algorithms are used in practice when there is no real alternative. eg. bin packing for CNC/laser machines (self-plug svgnest.com)

Re: Evolution Is the New Deep Learning

#170

Post by oldandtired »

tree_of_item wrote: post #121
dorgo wrote: post #120

Earlier quoted context omitted.

> My gut feeling is that it is hubris to think that we are going to "figure out" intelligence with increasingly sophisticated mathematical models anytime soon. We did it already. Compter understand language, translate it, react to it. They can recognize items on a picture. Is there a task left which can't be done by computers better and faster than by humans? >Almost by definition, if we can analytically understand i…

> Is there a task left which can't be done by computers better and faster than by humans? Are you serious? You think we're done?

Probably better if you gave a task example like being a mother or a father or a grandparent or an uncle or an aunt or a mentor or a friend or anything to do with human interaction.
Post reply on HN