[iacoposk8]

Hello everyone!
I would like to learn how to handle different projects intelligence artificile (possibly with python).
Googling seems that the libraries are the most common Scikit learn and Pybrain.
These two libraries use very different approaches, the first and most statistical, the second with neural networks.
1) in addition to the statistical method and neural there are other methods?
2) what method it will ensure better results for supervised learning (classification, regression) and unsupervised?

In general my question is that I do not know where to start, there are several algorithms to do the same thing (for example, facial recognition or voice you can do both with statistical methods, both with neural networks) and do not know where to start studying.

thanks

[ivan.moony]

hi there

If you want to build a chatbot then try learning AIML language. If you seek for more intelligent behavior, you can try learning math logic and theorem proving (maybe you can mix it with AIML to get a smarter chatbot). Neural networks are good for recognizing images and speech, but I think there is more that neural networks can do.

[Ultron]

I am no teacher nor experienced tutor, therefore I can only share you my short story...


I started out as somebody with an insanely strong desire to build a Jarvis-like program, much like the original from Iron Man. My previous knowledge and interests involved astronomy, physics, basic programming and a young interest in robotics. How did I begin learning? I just looked at other projects, improved my programming knowledge and occasionally read an article on Wikipedia regarding a certain subject within the machine learning domain.


I was already a few months into studying before I found out that what I wanted to do was in fact something called "Artificial Intelligence".


So my recommendation is to picture your goal and begin in whichever way you personally believe it is best. As time passes and experimentation goes on you will gradually find out the things you need to learn - these are very specific per person and project, hence why I have never found those 'how to get started' books and tutorials useful.


You define and explore your own set of needs, and slowly learn and evolve towards your goal. And remember - a house's most important part is it's foundation, so make sure your's is a tough one! Also don't forget that mistakes can only make you better. Good luck on your journey!

[Art]

Wow, Ultron...I'm impressed with such sage advice you have given. I was practically thinking that as I was reading along. Very nicely presented and some great advice for us all no matter our goal!

[Freddy]

Hi and welcome from me too

I've learnt a lot from the people here, so I think touching base with other people who are interested in the same kind of things is the first step to take.

Ask questions, start some debates, these things will help you learn.

For more hands on stuff Ivan has a good idea. Take a look at the things that are easier to get started with. Pattern matching systems are a good place, meaning things like AIML, ChatScript, RiveScript and others.

There's a lot of information here in various threads, take a look around. Good luck with your endeavour

[8pla.net]

My advice is to start as simple as possible...



INPUT

Input stimulus from human.   Example, "Hello!  Hey let's chat."

PROCESS

Process stimulus to match an A.I. response.   Example, "HELLO" =>  "Hi there!"

OUTPUT

Output response from A.I.  Example, "Hi there!"