Monthly Archives: November 2012

My New Learning Experience

I have always been quite confident in my learning ability. I believe for any given topic, I would be able to understand the logic behind and apply those knowledge to solve (sadly, but true) exam problems within a short amount of time. From school to university, even until early this year.

This level of confident has decreased recently in a good way I think. It reminds me that there are topics in field even I am most familiar with and interested in require significant effort to understand not to mention master or even contribute.

The two courses I taken via Coursera from Sep are Neural Network & Probability Graphic Model. Most of my learning is to watch the lecture videos while I commuting between home and office. I didn’t put in enough effort to really read through the slides and research on further materials mentioned by the instructor. I found myself missing quite a number of knowledge point. Especially in NN, many incitation and techniques introduced are very alien to me. Not only I can’t understand why do they use those tricks to train a network, but the exact difference between techniques.

Quizes for these 2 courses are still quite manageable, even though I am not fully understand what the lecturer said. However, those programming assignments are really big headache to me. Sometimes I spend more than 10 hours on 1 assignment, and still cannot figure out the right way. Sometimes I have to rely on reverse engineering by guess the expected result via trial and error.

It is a bit disappointed when I read that the answers for those programming assignment will not be released even after the course ended. It would continue be a status of half-half for me, even I can score perfectly by bootstrapping the answers.

After a few more hours on the assignment last night, I decided to stop. I will keep the assignment in my “Someday: ToDo” list when I have the opportunities to really go through the material thoroughly again.

Back to the original purpose of this post, I am here to remind myself that in order to be an expert in an even narrowly defined field, I need to prepare myself mentally.  Knowledge and skills in this world are so diverse and profound that so many smart people have contribute their lives. I should not expect a shortcut to lead me there.


EDIT: Turns out the NN staff point us the right direction with an excellent post in the forum who carefully explained the algorithm.

And it turns out that I was distracted by the ret=loss() function provided in the sample. My weight decay is totally off. I should have use what I learned from the Machine Learning by Andrew Ng on the regulation term.



Filed under Learn

10 Years From Now

Where do I want to be 10 years from now?

I could continue to work as an employee in a few companies. With some luck, I may become a middle manager in charge of a few systems and leading a few teams. I may have higher pay and live in a larger house located at a better location and drive a better car that can be parked nearer to my office. I would be able to choose a better seat in the office (most likely at the corner near windows).  I may get to evaluate the young and have the right to promote those I think performed better during the year.

But there are a few snapshot that I imaged if I follow that path made me laugh at myself. Yes, according to business convention here, bosses choose their seat window corner seat first. But due to some randomness, my boss’ boss is at 2 seats on my right near the window. As a result, he constantly needs to pull the curtain up and down to balance the reflection on his monitor.  Well, because I seated far from the window, stable supply of electricity save me all those troubles.

And yes, the big boss have a fancy big house located in a well-established neighborhood. But excluding the 8 hours of sleeping time (may be less, assume 6 hours only), he can only enjoy 3~4 hours a day there, as I assume he would have to spend more than 12 hours near my seat during the day.

I assume he drives a fancy car as well, as I have yet to meet him while he is driving. He would have to make a tradeoff between how long he wants to stay in his big house or in his fancy car due the rush hour traffic in CBD.

What’s next? Oh, while I am waiting for his appraisal at the end of the year, he had just gone through his with his boss who is holding our feedback to him as well. And so far as I know, we get a big treat from him at year end, but he may not have such a generous boss.

Well, I can’t give an answer for the question in this post, but a general principle for the path I need to choose is to choose differently.

The lesson of Buffett was: To succeed in a spectacular fashion you had to be spectacularly unusual.
(Lewis, Michael (2010-05-12). The Big Short: Inside the Doomsday Machine (p. 35). Norton. Kindle Edition.)

CAUTION: I am not criticizing people, I just record my imagination.

Leave a comment

Filed under Think