Loss Function

Loss Function: how good a model is. The lower the better, it means that is very accurate in predicting

Minimize = loss function = Maximum accuracy!

We can achieve this loss function by:

• Softmax: soft probability smaller than x, max amplifies probabilities of target $x_i$. Maps arbitrary values $x_i$ to probability distribution $p_i$
  • $softmax(x_i)=\frac{\exp (x_i)}{{\sum }_{j=1}^n\exp (x_j)}=p_i$
• more optimized solutions
• negative sampling