Let’s use a simple example to explain some terms. For one dataset of points in a 2-D plane, there might be many curves that can fit these points (each curve correponds to a machine learning model).
Do you really know neural networks' optimizer?
Do you really know these optimizers in neural network training?
Experience in training CNN
We usually see two problems when training a CNN. The first one is that the model performs bad on the training data (optimization problem). The second one is that the model performs good on the training data but bad on the validation data (overfitting).
Do you really know CNN basics?
What is the change from ordinary neural network to convolutional neural network?
Unit testing in Python
What is unit testing?
When doing unit testing, you break your codes into small units (mostly functions), and test if each unit works as expected. Generally the tests are written in the form of functions that will determine whether a returned value equals the value you were expecting when you wrote the function.
ResNeXt paper note
ResNeXt is a new CNN architechture following the ResNet. The paper is here.
Do you really know the linear classifier basics?
Let’s talk about a simple linear classifier: $$f(x_i, W, b) = Wx_i + b$$
What does one row of the weight matrix represent?
Python random module: why we need to set seed?
I was Googling what random.seed() does and found that the random module in Python in fact implements pseudo-random number generators.
Python os.path module examples
os.path.abspath(path)
No matter what you pass into os.path.abspath(), the path is seen as a relative path. It is relative to the directory from where you are executing your code. So the return value will concatenate your current directory with path.
Python Unicode
Python 2.x’s support for Unicode was a messy problem for me when I started learning Python. Today I read through the official tutorial and want to take note of it.
Note: In Python 3, there are some changes. This post is only based on Python 2.