Bøger af Raúl Rojas

This book describes the historical development of the architectures of the first computers built by the German inventor Konrad Zuse in Berlin between 1936 and 1945. Zuse's machines are historically important because they anticipated many features of modern computers.Specifically, these include the separation of processor and memory, the ability to compute with floating-point numbers, a hardware architecture based on microprogramming of the instruction set, and a layered design with a high-level programming language on top. In fact, Zuse's early computers are closer to modern computers than the Harvard Mark I or ENIAC, two other contenders for the title of "world's first computer." The theoretical program first conceived by Zuse in 1936/37 was fulfilled with a series of machines built before and during World War II: the Z1, Z2, Z3, and Z4. Separate chapters deal with the architecture of each computer, culminating in the description of Plankalkül, the first proposal for a high-level programming language.Students of the sciences and practitioners of computer science should have no trouble following the material. The concise introductory summary sets the reader on the historical path to retrace this remarkable intellectual adventure.

In this book, theoretical laws and models previously scattered in the literature are brought together into a general theory of artificial neural nets. Always with a view to biology and starting with the simplest nets, it is shown how the properties of models change when more general computing elements and net topologies are introduced.

This book bridges the gap between Soft Computing techniques and their applications to complex engineering problems.