# Changeset 639

Ignore:
Timestamp:
Sep 6, 2006, 2:18:46 PM (15 years ago)
Message:

Fixed documentation bugs

Location:
trunk
Files:
2 edited

### Legend:

Unmodified
 r616 inline double beta_err(void) const { return sqrt(beta_var_); } /// /// This function computes the best-fit linear regression /// coefficients \f$(\alpha, \beta)\f$ of the model \f$y = /// \alpha + \beta (x-m_x) \f$ from vectors \a x and \a y, by /// minimizing \f$\sum{w_i(y_i - \alpha - \beta (x-m_x))^2} \f$, /// where \f$m_x \f$ is the weighted average. By construction \f$/// \alpha \f$ and \f$\beta \f$ are independent. /// /** This function computes the best-fit linear regression coefficients \f$(\alpha, \beta)\f$ of the model \f$y = \alpha + \beta (x-m_x) \f$ from vectors \a x and \a y, by minimizing \f$\sum{w_i(y_i - \alpha - \beta (x-m_x))^2} \f$, where \f$m_x \f$ is the weighted average. By construction \f$\alpha \f$ and \f$\beta \f$ are independent. **/ void fit(const utility::vector& x, const utility::vector& y, const utility::vector& w); /// /// Function predicting value using the linear model: \f$y = /// \alpha + \beta (x - m) /// Function predicting value using the linear model: /// \f$ y =\alpha + \beta (x - m) \f$/// double predict(const double x) const { return alpha_ + beta_ * (x-m_x_); } { return sqrt(alpha_var_ + beta_var_*(x-m_x_)*(x-m_x_)+s2_/w); } /// /// estimated error @a y_err \f$ y_err = \sqrt{ Var(\alpha) + /// Var(\beta)*(x-m)^2 }. /// /** estimated error \f$y_{err} = \sqrt{ Var(\alpha) + Var(\beta)*(x-m)} \f$. **/ inline double standard_error(const double x) const { return sqrt(alpha_var_ + beta_var_*(x-m_x_)*(x-m_x_) ); }
 r627 The polynomial kernel of degree $N$ is defined as $(1+)^N$, where  is the linear kernel (usual scalar product). For the weighted case we define the linear kernel to be $=\sum w_xw_yxy}$ and the case we define the linear kernel to be $=\sum {w_xw_yxy}$ and the polynomial kernel can be calculated as before $(1+)^N$. Is this kernel a proper kernel (always being semi