Error when calling Cuda kernel?

Question

GPGPU

Good afternoon, the program has a class:

class neuralNet {
  float input_nodes;
  float hidden_nodes;
  float output_nodes;
  float learning_grade;
  float* wih;
  float* who;
  
public:
  neuralNet(int in, int hid, int out, float lr);
  ~neuralNet();
  float*activation_function(float* a, int n);
  void train(float*inputs, float*targets);
   void query(float*inputs);
   __global__ void query_kernel(float*inputs_d); // (2)
};

When called in main:

n.query_kernel << <60000, 1 >> > (inputs_d); // (1)

It gives the following errors...
1) a pointer to a bound function may only be used to call the function
2) illegal combination of memory qualifiers
What is it and how to get around? Thank you very much for any advice / guidance ... I'm just learning and I will be grateful for everything.