diff --git a/src/neural.c b/src/neural.c
index 7b6f0cc..c68391c 100644
--- a/src/neural.c
+++ b/src/neural.c
@@ -66,7 +66,7 @@ neural_randomize(Neural_Network *self) {
               nl->layer_size_next, f);
         for (int j = 0; j < nl->layer_size; j++) {
             for (int k = 0; k < nl->layer_size_next; k++) {
-                nl->neurons[j].synapses[k] = UINT64_MAX / rand_vals[k]
+                nl->neurons[j].synapses[k] = UINT64_MAX / rand_vals[k];
             }
         }
     }
@@ -74,7 +74,6 @@ neural_randomize(Neural_Network *self) {
 
 float *
 neural_loadData(Neural_Network *self, const char *filename) {
-    Neural_Layer *nl;
     FILE *f;
     char *file_data;
     float *retval;
@@ -87,8 +86,6 @@ neural_loadData(Neural_Network *self, const char *filename) {
 
     f = fopen(filename, "r");
 
-    nl = self->layers[0];
-
     fread(file_data, sizeof(char), 9*8, f); // 9*8 - 8*8 value matrix + newlines
     for (int i = 0; i < 8*8; i++) {
         if (file_data[read_cursor] == '\n') {
@@ -158,12 +155,16 @@ neural_backprop_down(Neural_Network *self, size_t neuron, size_t layer) {
 
 int
 neural_train(Neural_Network *self,
-             const char *testdata,
+             const float *testdata,
              const float *testresult) {
-    float *testdata_converted;
-    testdata_converted = malloc(self->layers[self->layer_count-1]->layer_size * sizeof(float));
+    float *retval;
+    int k, i;
 
-    return 0;
+    retval = malloc(self->layers[self->layer_count-1]->layer_size * sizeof(float));
+    k = 0;
+    i = 0;
+
+    return retval;
 }
 
 int