A multi-hop amplify-and-forward (AF) relay network can emulate a fully connected (FC) neural network layer via over-the-air (OTA) computation. However, achieving high emulation accuracy requires accurate channel state information (CSI) across all links in the multi-hop network. In this work, we investigate the impact of CSI errors on classification performance. We propose five heuristic schemes for allocating the total channel training time (pilots) across hops and compare their effectiveness. Numerical results reveal a clear trade-off between channel training overhead and classification accuracy. In particular, with sufficient pilot power and balanced allocation of channel training resources, the system can achieve classification accuracy close to that of the digital baseline.