Bubbling thoughts

Notation is a kind of technology. Used heavily in mathematics to express a very specific idea which could be hard and complex to express it using human language. I have never think it in this way, very interesting. So, study notation or mathematics symbol (some of them in Greek letters I think like Zigma or all them ? yes like + 'plus  sign) is like leveraging technology ...just like using a smartphone to make enhance our lives:)

I have been learning about deep learning and machine learning in general. One struck me is that all of this mapping from input to output could be done accurately by the machine, in some respect even better than human. It got me thinking that those mapping from input to output, many people would be easily deceived that it is a causation relationship but in fact many of them would be in correlation relationship. this is tricky, because the confusion between the two would be dangerous. Or at least in some applications we could say that is not just one. two or even x inputs that causes a certain output. I think the world kind of confused which one is correlation and which one is causation. It is very time consuming and energy intensive to establish a causation theory. Most people would just give up or mislead their way of thinking.

in deep learning you don't have to do feature selection, this is automated by the deep learning algorithm by looking at the patterns of the data. we just feed it in and see the output classification. Talking about automation, this is a time saver for human being isn't it? The point why computer is really helpful to us is the fact that it could automate task. Now, do we need to understand how the machine do it? I think this is just a matter of trust or fear from humanity to machine. We don't need to understand anything, but sometimes what it matters is solving the problem. Like a doctor giving the medicine to a patient, granted he or she will have the understanding of how the medicine works into human body. This understanding however is 'limited', the doctor kind of 'trust' the work of the people who created those medicine that it will do no harm to the body. But the truth of the matter is it does not work always that way. There is a degree of 'blac...

difference between machine learning and traditional programming. In traditional programming we tell the machine what to do or the decision making process to reach a certain goal. Like in order to identify a person, look for nose, look for eye, look ear, look for mouth and etc. but with machine learning we don't tell the machine what to do how to reach a goal. So, if the goal is to recognize human face then we give the machine many faces of human being and let the machine learn it on its own, instead of telling the machine what to do. This is much like the learning process of human being, where to accomplish a skill we could tell the human specific instructions of what to do or we could just give them the outcome and let the human figure out how to do it. this could be done through trial and error, and through error human could learn. So for example instead of tellling human what to in order to set up a succesfull business steo by step. Say, think about product and service tha...

The meaning of learning should encompass everything that we do, not just the subject matter. this means when we say we are learning math, is not just we are learning math but we also learning the preparation to get that math ready and the after math too. In this was we are managing our expectation in a way that everything that we do involve patience and making mistake. this is why we see that the subject matter is the important thing, but also the before and after. If we could have that kind of mindset then we will have a living in the present moment all the time. Because now suddenly there is no end and beginning, everything is like a continuous flow.

is to create something small ...that is the short answer. Linux created from something small about 25 years ago, only from 1 person who is trying to create an OS besides the gnu or something like that ..from the prevailing OS that was much more popular at that time. This was i think even DOS was invented. the key point there is start with your own problem, and to make the user base happy and keep on improving there, and also the key is make it open and/or collaborative so other people could join in improving the OS. I think that is very empowering, because now people could not just give feedback but also could build it on their own that improvement if they want too. the key take away point: - start with your own problem (start small) - launch it and get feedback from the end-user (not mediator) - improve based on the feedback - make it collaborative another example is airbnb.com google probably is one of the answer too can you think of something else?