Neural computation arises from the capacity of nervoustissue to process information and accumulate knowledge in anintelligent manner. Conventional computational machines haveencountered enormous difficulties in duplicatingsuchfunctionalities. This has given rise to the development ofArtificial Neural Networks where computation is distributedover a great number of local processing elements with a highdegree of connectivityand in which external programming isreplaced with supervised and unsupervised learning. The papers presented in this volume are carefully reviewedversions of the talks delivered at the InternationalWorkshop on Artificial Neural Networks (IWANN '93) organizedby the Universities of Catalonia and the Spanish OpenUniversity at Madrid and held at Barcelona, Spain, in June1993. The 111 papers are organized in seven sections:biological perspectives, mathematical models, learning,self-organizing networks, neural software, hardwareimplementation, and applications (in five subsections:signal processing and pattern recognition, communications,artificial vision, control and robotics, and otherapplications).