Synaptic plasticity in the living body, which is dependent on the order of and interval between pre- and post-synaptic spikes (STDP), has been observed by physiological experiments. Recently, many investigators have attempted to suggest the associative memory using electronics circuits. In this paper, we propose an associative memory model using a pulse-type hardware neural network with the STDP synapses. As a result, it is shown that the synaptic weight changes depending on the input current patterns of temporal sequence pulses. Furthermore, it is shown that if the output stimulus is lacking, the proposed network model can recognize this by the reading of input current patterns.