Info on Smalltalk DSLs or Metaprogramming...

>> I'm fine excepting your definition of DSL. However, I still
>> think there should be a way to describe the more specific,
>> interpreted case. There's a lot of value in looking at the
>> interpreted case as a separate technique. And that's hard to
>> do if you say DSL and everyone just makes their own assumptions.
>>
>> -Rich-
>
> What's wrong with simply saying interpreted DSL?
>
>

> Hello Rich,
>
>
>>> This (reinforcement learning) is said to be slow. What number of
>>> inputs and how many neurons would such a brain have? How many  
>>> agents?
>
> RW> Regarding reinforcement learning, I've seen this complaint form  
> other
> RW> EE people, and I never really understood it. Perhaps you could  
> give
> RW> me an example. In my opinion, it really depends.
>
> regarding slowness, I'm an absolute beginner on neural nets and only
> read about how much rounds of training it needs. Currently I'm in the
> stage of: "Is my data representation suitable for processing by a
> (which type of?) neural net?"
>
> Going through: training the net -> evaluate network performance ->
> change data representation or network topology .....
> feels slow in absolute terms.
>
> And a single layer perceptron behind a self organizing feature map
> trains much faster than a multilayer network (only a few of the nodes
> are trained) with comparable results (in my special case).
>
> As soon as I know that a training will yield the "best possible"
> result, I will be cool if a computer needs to run a weekend to train a
> network.
>
> On the other hand, soon after I reach that state, the subject will get
> boring :-))
>
> RW> Not off hand (though I always recommend searching on http://
> RW> citeseer.ist.psu.edu/). If you're just trying to train the  
> weights,
> RW> you can just read the bits into an array and use that as your  
> genome.
> RW> If you want to evolve both the weights and the size/topography,  
> you
> RW> need more sophisticated methods. I know some people have worked on
> RW> different ways to encode neural nets (basically compressing the
> RW> layout/weight information, much the way our DNA compresses all the
> RW> information needed to build a human body).  I can't find the
> RW> reference in my notes right now, however.
>
> Thanks!
>
>
> Herbert                            mailto:[hidden email]
>
>

> > Modulo the quality of the comments in the code that are being used,
> > it's the presentation that can make the difference. A form of
> > browser  that can gather linked comments from methods and classes
> > and present  them in a neatly intelligible form is surely an
> > improvement over  scattered snippets?
>
> Is not the standard Smalltalk browser such a browser?  How would some
> other browser, using the same data, be able to somehow present the
> information better than the Smalltalk browser?  If such a great
> feature existed, wouldn't we simply add it to the existing Smalltalk
> browser?