def update_parameters(parameters, grads,learning_rate,iter_no,method = 'SGD',opt_parameters=None,beta1=0.9,beta2=0.999):
    """
        Update parameters using gradient descent

        Arguments:
        parameters -- python dictionary containing your parameters
        grads -- python dictionary containing your gradients, output of L_model_backward
        method -- method for updation of weights
                  'SGD','SGDM','RMSP','ADAM'
        learning rate -- learning rate alpha value
        beta1 -- weighted avg parameter for SGDM and ADAM
        beta2 -- weighted avg parameter for RMSP and ADAM

        Returns:
        parameters -- python dictionary containing your updated parameters
                      parameters["W" + str(l)] = ...
                      parameters["b" + str(l)] = ...
                      opt_parameters
    """

    L = len(parameters) // 2 # number of layers in the neural network
    if method == 'SGD':
        for l in range(L):
            parameters["W" + str(l+1)] = parameters["W" + str(l+1)] - learning_rate*grads["dW" + str(l + 1)]
            parameters["b" + str(l+1)] = parameters["b" + str(l+1)] - learning_rate*grads["db" + str(l + 1)]
        opt_parameters = None
    elif method == 'SGDM':
        for l in range(L):
            opt_parameters['vdb'+str(l+1)] = beta1*opt_parameters['vdb'+str(l+1)] + (1-beta1)*grads["db" + str(l + 1)]
            opt_parameters['vdw'+str(l+1)] = beta1*opt_parameters['vdw'+str(l+1)] + (1-beta1)*grads["dW" + str(l + 1)]
            parameters["W" + str(l+1)] = parameters["W" + str(l+1)] - learning_rate*opt_parameters['vdw'+str(l+1)]
            parameters["b" + str(l+1)] = parameters["b" + str(l+1)] - learning_rate*opt_parameters['vdb'+str(l+1)]
    elif method == 'RMSP':
        for l in range(L):
            opt_parameters['sdb'+str(l+1)] = beta2*opt_parameters['sdb'+str(l+1)] + \
                                                     (1-beta2)*np.square(grads["db" + str(l + 1)])
            opt_parameters['sdw'+str(l+1)] = beta2*opt_parameters['sdw'+str(l+1)] + \
                                                           (1-beta2)*np.square(grads["dW" + str(l + 1)])
            parameters["W" + str(l+1)] = parameters["W" + str(l+1)] - \
                                       learning_rate*(grads["dW" + str(l + 1)]/(np.sqrt(opt_parameters['sdw'+str(l+1)])+10**-8))
            parameters["b" + str(l+1)] = parameters["b" + str(l+1)] - \
                                       learning_rate*(grads["db" + str(l + 1)]/(np.sqrt(opt_parameters['sdb'+str(l+1)])+10**-8))
    elif method == 'ADAM':
        for l in range(L):
            opt_parameters['vdb'+str(l+1)] = beta1*opt_parameters['vdb'+str(l+1)] + (1-beta1)*grads["db" + str(l + 1)]
            opt_parameters['vdw'+str(l+1)] = beta1*opt_parameters['vdw'+str(l+1)] + (1-beta1)*grads["dW" + str(l + 1)]
            opt_parameters['sdb'+str(l+1)] = beta2*opt_parameters['sdb'+str(l+1)] + \
                                                                  (1-beta2)*np.square(grads["db" + str(l + 1)])
            opt_parameters['sdw'+str(l+1)] = beta2*opt_parameters['sdw'+str(l+1)] + \
                                                                   (1-beta2)*np.square(grads["dW" + str(l + 1)])

            learning_rate = learning_rate * np.sqrt((1-beta2**iter_no)/((1-beta1**iter_no)+10**-8))
            parameters["W" + str(l+1)] = parameters["W" + str(l+1)] - \
                                       learning_rate*(opt_parameters['vdw'+str(l+1)]/\
                                                      (np.sqrt(opt_parameters['sdw'+str(l+1)])+10**-8))
            parameters["b" + str(l+1)] = parameters["b" + str(l+1)] - \
                                       learning_rate*(opt_parameters['vdb'+str(l+1)]/\
                                                      (np.sqrt(opt_parameters['sdb'+str(l+1)])+10**-8))

    return parameters,opt_parameters