def dsquared_loss(y_pred, y_train):
m = y_pred.shape[0]
grad_y = y_pred - util.onehot(y_train)
grad_y /= m
return grad_y
def dsquared_loss(y_pred, y_train):
m = y_pred.shape[0]
grad_y = y_pred - util.onehot(y_train)
grad_y /= m
return grad_y
def squared_loss(model, y_pred, y_train, lam=1e-3):
m = y_pred.shape[0]
data_loss = 0.5 * np.sum((util.onehot(y_train) - y_pred)**2) / m
reg_loss = regularization(model, reg_type='l2', lam=lam)
return data_loss + reg_loss
def squared_loss(model, y_pred, y_train, lam=1e-3):
m = y_pred.shape[0]
data_loss = 0.5 * np.sum((util.onehot(y_train) - y_pred)**2) / m
reg_loss = regularization(model, reg_type='l2', lam=lam)
return data_loss + reg_loss
