Skip to main content

deep learning 1

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 'blackbox' in the medicine of how it will effect the body, cells, etc. So, in this case the doctor might have an 'overview' understanding of how the medicine will works but at the same-time there is a degree of 'unknown'.

So, this bring me back to the idea of deep learning being able to automate the feature selection process that normally we human do it manually or the need of having a domain expertise.

I think this is why deep learning is so powerful because the computer does what it does best, which is sequential computational processing that is no match with human being. It could see patterns, particularly the bigger the data the better it is for machine to do this ...and they have the superpower in processing big chunks of data in a sequential manner.

So, we have to make a jump to deep learning for this reason and kind of make the classical manual feature selection algorithm kind of obsolete? I don't know the answer to that question, only time will tell but my intuition said 'yes'!

I believe as of now there is still space of classical machine learning especially if the data does not involved of huge amount of data. In this case vision problems specifically would be in the realm of deep learning because of its sheer amount of data.


Comments

Popular posts from this blog

Very Old Youtube video ... babbling about myself having mid-life crisis

Enjoy :)

Keep your life options open till you are sure

I have been contemplating this quotes from Naval Ravikant: First, In making decision if you are not sure, then don't do it.
Second, if it boils down only 2 options and it's fifty/fifty then choose the one that is painful in the short term and bring equanimity in the longer term. Like should i do sports this today or not? Should I eat healthy food or not?

The first one it seems you have 1 option to choose vs myriads of options. This seems to me if people have some money in their pocket. so they have this liberty to keep their option in life to always open.

Especially we are now living in an exponentially option abundance in our time because of the proliferation of technology. So, ideally we always want to keep our options/choice open in life until we are pretty damn sure we want to do it whole heartedly. Meaning not just with your mind but also with your heart and soul. I think this boils down do what you want! Not what the society/parents/obligation tells you what to do! In ot…

The Case for Tesla

What is Tesla moat? Moat is define by what is the core strength of company(Tesla) that prevent other players to compete with it and as such unable to provide value to the market.

Scale Effects:
Tesla has been ramping up their car production up to 6000/week, they have been learning the hard way to ramp up their production hell season.

The gigafactory: They have investing a lot in their gigafactory for their battery technology and according to Ark Invest and Mark Munro (on youtube) their battery technology is superior (about 3 years advance than others) plus the fact they own their own factory. The battery is the ICE world is like the engine part. While BMW, Mercedez and other cars company seems to just outsource their battery technology to third party instead of making on their own.

So, there are 2 points here: one is the battery technology is superior, and two is Tesla control the battery availability and they make sure the supply is there. The first point probably is kind of debatabl…