Creating tests for Kelp.Net is incredibly simple. Each test that you author needs only a single Run function exposed. The rest is your logic as to how you want your network to operate. The general guidelines for your Run function would be:

• Load data (real or simulated):

Real[][] trainData = new Real[N][];
             Real[][] trainLabel = new Real[N][];
 
             for (int i = 0; i < N; i++)
             {
                 //Prepare Sin wave for one cycle
                 Real radian = -Math.PI + Math.PI * 2.0 * i / (N - 1);
                 trainData[i] = new[] { radian };
                 trainLabel[i] = new Real[] { Math.Sin(radian) };
             }

• Create your function stack:

FunctionStack nn = new FunctionStack(
                 new Linear(1, 4, name: "l1 Linear"),
                 new Tanh(name: "l1 Tanh"),
                 new Linear(4, 1, name: "l2 Linear")
             );

• Select your optimizer:

 nn.SetOptimizer(new SGD());

• Train your data:

for (int i = 0; i < EPOCH; i++)
            {
                Real loss = 0;
                for (int j = 0; j < N; j++)
                {
                    //When training is executed in the network, an error is returned to the return value
                    loss += Trainer.Train(nn, trainData[j], trainLabel[j], new MeanSquaredError());
                }
                if (i % (EPOCH / 10) == 0)
                {
                    RILogManager.Default?.SendDebug("loss:" + loss / N);
                    RILogManager.Default?.SendDebug("");
                }
            }

• Test your data:

            RILogManager.Default?.SendDebug("Test Start...");
            foreach (Real[] val in trainData)
            {
                RILogManager.Default?.SendDebug(val[0] + ":" + nn.Predict(val)[0].Data[0]);
            }