### abstract

- We present algorithms for initializing networks that use a convolutional network coding scheme and that may contain cycles. During the initialization process every source node transmits basis vectors and every sink node measures the impulse response of the network. The impulse response is then used to find a relation between the transmitted and the received symbols, which is needed for a decoding algorithm and to find the set of all achievable rates. An initialization process is needed if the network is unknown or if local encoding kernels are chosen randomly. Unlike acyclic networks, for which it is enough to transmit basis vectors one after another, the initialization of cyclic networks is more complicated, as pilot symbols interfere with each other and the impulse response is of infinite duration.