In biological systems, animals exhibit organized behavior that arises from localized interactions. The interaction is implemented through information exchange, either directly or indirectly. Adaptive networks, consisting of a collection of nodes with learning abilities that interact with each other to solve distributed inference problems in real-time, are well-suited to model these kinds of behavior. Usually the information exchange between two nodes is imperfect and the data from neighbors are noisy. In this paper, we examine the effect of noisy communication links on network performance and derive an optimal strategy for adjusting the combination weights.