Construction in progress ...

... if you put them in practice. In the end, you cannot say that an idea is good only by reasoning about it. You may always miss something when you're simulating the future in your head. You need to actually do it to test if it works or not, usually multiple times so that you know that if you got the expected results this was not by chance. Another way of thinking about it is that let's say you are reading about some rule. You shouldn't think it is true or that it applies in any conditions because you trust who wrote it. You have to think yourself about it maybe more than you usually do by instinct when you are encounter anything new. Which basically means to think critically. So ideas are good if you put them to practice. But if you apply this pattern to the process of reasoning about the patterns themselves it just means to think critically since the patterns are about thinking about how to think.  

As in why do I write? Just because I believe that most of the time the reason we are not happy is that we get caught up in unhealthy thinking. And this unhealthy thinking happens because we focus so much on the immediate inconveniences that we forget some good thinking rules that we found in more happier times. And I feel that if I just write them down this thinking patterns may just become habits so that I remember to use them when I need them the most. So basically I write so that I don't forget what I think them to be general patterns of good thinking. Because they usually don't teach you in school (enough about) this kind of things, more precisely how to think. I guess it is implied that since you are thinking all day long then obviously you know how to do it. But actually it doesn't mean that you are doing it right! And it may not be obvious how to correct your way of thinking until you somehow find out from someone wiser. As an example when confronting with a ma...

While deep learning (or other types of machine learning) seems to be the answer to most of the hard problems in computer science like computer vision, prominent figures of the field admit that advancing in the area of general intelligence will require entirely different methods. Geoffrey Hinton says that he is "deeply suspicious" about back-propagation, the technique used to train neural networks, and that "My view is throw it all away and start again" . Yoshua Bengio, in a conference presentation called " Creating Human Level AI ", says that we are "still far away". "All industrial successes are based on pure supervised learning" "Still learning supeficial clues that do not generalize well outside of training contexts and make it easy to fool trained networks: Current models cheat by picking on surface regularities, e.g. , background greenery implies that probably an animal is present " "Still unable to do a good...