摘要:
Neural NetworksThe ‘one learning algorithm’ hypothesisNeuron-rewiring experimentsModel RepresentationDefineSigmoid(logistic) activation functionbias unit input layeroutput layerhidden layer\(a_i^{(j)}... 阅读全文
摘要:
Regularization for Linear Regression and Logistic Regression Define Addressing over-fitting Manually select which features to keep. Model selection al 阅读全文
摘要:
h(x)\[\begin{align*}h_\theta(x) =\begin{bmatrix}\theta_0 \hspace{2em} \theta_1 \hspace{2em} ... \hspace{2em} \theta_n\end{bmatrix}\begin{bmatrix}x_0 \newline x_1 \newline \vdots \newline x_n\end{bmatr... 阅读全文
摘要:
Binary ClassificationDefineSigmoid Function Logistic Function\[ h_\theta(x) = g(\theta^Tx) \]\[ z = \theta^Tx \]\[ 0 \theta^Tx = 0\)Cost Function\[J(\theta) = \dfrac{1}{m} \sum_{i=1}^m \mathrm{Cost}(... 阅读全文
摘要:
Symbols:m = Number of training examplesx’s = “input” variable /featuresy’s = “output” variable / “target” variaable(x, y) = one training example\((x^{(i)}, y^{(i)})\) = \(i_{th}\) training exampleh(x)... 阅读全文