The mean squared error (or MSE or mean squared deviation (MSD)) measures the mean of the squared error between two values. That is
$$
MSE = \frac{1}{n} \sum_{i = 1}^{n} (V_i - W_i)^2
$$
for $W,V$ vectors.
Since we square, we have no negative values.
CommentsGuest Name:Comment:
[Standard_Functions] Softmax;;Default.aspx?id=2;;;;[Standard_Functions] Mean Squared Error;;Default.aspx?id=4;;;;[Standard_Functions] Coefficient of Determination;;Default.aspx?id=7;;;;[Standard_Functions] Arithmetic Mean;;Default.aspx?id=6;;;;[Standard_Functions] Sigmoid;;Default.aspx?id=10;;;;[Standard_Functions] ReLU;;Default.aspx?id=12;;;;[Vapnik–Chervonenkis_Theory] VC-Dimension;;Default.aspx?id=14;;;;[Neural_Networks] 1. Introduction with the XOR problem;;Default.aspx?id=1;;;;[Neural_Networks] 3. PyTorch for learning the XOR Problem;;Default.aspx?id=5;;;;[Regression] 1. Introduction;;Default.aspx?id=8;;;;[Regression] 2. Using Vector Notation;;Default.aspx?id=9;;;;[Regression] 1. Introduction;;Default.aspx?id=15;;;;[Regression] 2. Deriving the model;;Default.aspx?id=16;;;;[Regression] 3. Multinomial Logistic Regression;;Default.aspx?id=17;;;;[PyTorch] 1. Linear;;Default.aspx?id=13;;;;