Neural cryptography is the application of artificial neural networks (ANNs) in the subject of cryptography. The functionality of this solution is based on a tree parity machine (TPM). It uses ANNs to perform secure key exchange between network entities. This brief proposes improvements to the synchronization of two TPMs. The improvement is based on learning ANN using input vectors that have a wider range of values than binary ones. As a result, the duration of the synchronization process is reduced. Therefore, TPMs achieve common weights in a shorter time due to the reduction of necessary bit exchanges. This approach improves the security of neural cryptography.