Guocheng Wei

I will share my side projects, paper readings, trending news, and my life here with you.

Coursera Notes

Week 5 - Machine Learning

Neural Network Cost Function, Backpropagation Algorithm, Unrolling Parameters, Gradient Checking, Random Initialization

Guocheng Wei

4 minute read

ml stanford thumbnail

$$ \begin{gather} J(\Theta) = - \frac{1}{m} \sum_{i=1}^m \sum_{k=1}^K \left[y^{(i)}_k \log ((h_\Theta (x^{(i)}))_k) + (1 - y^{(i)}_k)\log (1 - (h_\Theta(x^{(i)}))_k)\right] + \frac{\lambda}{2m}\sum_{l=1}^{L-1} \sum_{i=1}^{s_l} \sum_{j=1}^{s_{l+1}} ( \Theta_{j,i}^{(l)})^2 \end{gather} $$

Week 4 - Machine Learning

Non-Linear Hypotheses, Neural Network Model, Multiclass Classification, Regulation

Guocheng Wei

5 minute read

ml stanford thumbnail

If create a hypothesis with r polynominal terms from $n$ features, then there will be $\frac{(n+r-1)!}{r!(n-1)!}$. For quadratic terms, the time complexity is $O(n^{2}/2)$. Not pratical to compute.

Week 3 - Machine Learning

Classification, Representation, Logistic Regression Model, Multiclass Classification

Guocheng Wei

8 minute read

ml stanford thumbnail

Now we are switching from regression problems to classification problems. Don’t be confused by the name “Logistic Regression”; it is named that way for historical reasons and is actually an approach to classification problems, not regression problems.

Recent posts

See more



Passion in core network, ML, and software engineer. Love food, hiking, and snow skiing.