gradient <- function(theta, X, y){
  
  #   Compute gradient for logistic regression
  #
  #   grad <- costFunction(theta, X, y) computes the gradient of the cost
  #   for logistic regression w.r.t. to the parameters.
  
  # Initialize some useful values
  m <- length(y) # number of training examples
  
  # ====================== YOUR CODE HERE ======================
  # Instructions: Compute the partial derivatives and set grad 
  #               to the partial derivatives of the cost 
  #               w.r.t. each parameter in theta
  #
  # Note: grad should have the same dimensions as theta
  # 

  
  
  # ============================================================
  
  return(grad)
}