from : http://www.dowdandassociates.com/blog/content/howto-repair-windows-7-install-after-replacing-motherboard/

HowTo: Repair Windows 7 Install After Replacing Motherboard

So you’ve installed a new motherboard and now your existing, installed copy of Windows 7 won’t boot, failing somewhere before the logo finishes displaying with a quick blue screen? Well here’s one way to fix it.

You will need:

• Your motherboard drivers. Use CPUID(CPU-Z) to find the model number if you don’t have it handy.
• The archive program “7-Zip” available from http://www.7-zip.org/ installed.
• A cd writer and a blank cd or a thumb drive or a usb hard disk
• Your windows 7 install disc if you already tried the system repair option, or the system repair option on the windows boot options screen if it is there.
• Another, working, computer.

Get your motherboard drivers downloaded from the manufacturer’s website. If you don’t know the model number you can use CPUIDand locate the model number and manufacturer on the “Mainboard” tab:

In this example, the manufacturer is MSI (Micro-Star International), so we can get the drivers by a quick google search for “MSI Motherboard Driver Downloads.” The primary one you need is the IDE/AHCI/SATA driver files. After they’ve finished downloading, you need to extract them to a folder. You can do this by right clicking and selecting 7-Zip -> Extract to <Name of Driver Download>:

Copy the extracted folder to a cd, thumb drive, or external usb drive.

---

Go to the broken windows 7 machine. Either load the system repair option or boot off your windows 7 install disc. Once it boots, select your language and other things and hit next:

At the bottom of the window is an option that says “repair”, click this:

It will scan your drives, hopefully showing your windows drive. If so, let it try to repair automatically at least once. Come back to this point if that fails. You can click “no” here, and it will drop back to the window that shows your windows hard drive. Make sure the top radio button is selected and click next. It should bring up a list of links that you can click, the bottom one is “recovery console”, click that:

Eject the windows disc and put in the cd you burned if you burned one. You need to figure out which drive your cd/thumbdrive/external drive is - so try different drive letters and type dir until you see the one that has your folder. if you burned a cd, chances are it’s the D: drive(unless it was an HP or something, then it will be E:)if it’s a thumb drive or external hard drive and you only have 1 cd-rom, it’s the E: drive. Maybe F: – check it out. We might add a guide on how to do this at a future date.

once you have that figured out you need to type this

dism /image:c:\ /add-driver /Driver:X:\ /recurse

replace “X” with the drive letter from the previous step:

Hit enter and it should find the drivers you extracted into the folder in the second step.

after it does that, type “exit” and hit enter, then press the “Restart” button.

When windows boots it will take a LONG time to get all the updated drivers - but hey, it booted, right?

ML Maximum likelihood explaination

Discrete Random Variables

Suppose that you have a stochastic process that takes discrete values (e.g., outcomes of tossing a coin 10 times, number of customers who arrive at a store in 10 minutes etc). In such cases, we can calculate the probability of observing a particular set of outcomes by making suitable assumptions about the underlying stochastic process (e.g., probability of coin landing heads is p and that coin tosses are independent).

Denote the observed outcomes by O and the set of parameters that describe the stochastic process as θ. Thus, when we speak of probability we want to calculate P(O|θ). In other words, given specific values for θ, P(O|θ) is the probability that we would observe the outcomes represented by O.

However, when we model a real life stochastic process, we often do not know θ. We simply observe O and the goal then is to arrive at an estimate for θ that would be a plausible choice given the observed outcomes O. We know that given a value of θ the probability of observing O is P(O|θ). Thus, a 'natural' estimation process is to choose that value of θ that would maximize the probability that we would actually observe O. In other words, we find the parameter values θ that maximize the following function:

L(θ|O)=P(O|θ)

L(θ|O) is called as the likelihood function. Notice that by definition the likelihood function is conditioned on the observed O and that it is a function of the unknown parameters θ.

Continuous Random Variables

In the continuous case the situation is similar with one important difference. We can no longer talk about the probability that we observed O given θ as in the continuous case P(O|θ)=0. Without getting into technicalities, the basic idea is as follows:

Denote the probability density function (pdf) associated with the outcomes O as: f(O|θ). Thus, in the continuous case we estimate θ given observed outcomes O by maximizing the following function:

L(θ|O)=f(O|θ)

In this situation, we cannot technically assert that we are finding the parameter value that maximizes the probability that we observe O as we maximize the pdf associated with the observed outcomes O.