tailieunhanh - Speech recognition using neural networks - Chapter 3

Review of Neural Networks Trong chương này chúng tôi trình bày một đánh giá ngắn gọn về mạng lưới thần kinh. Sau khi đưa ra một số bối cảnh lịch sử, chúng tôi sẽ xem xét một số khái niệm cơ bản, mô tả các loại khác nhau của các mạng thần kinh và thủ tục đào tạo (với sự nhấn mạnh đặc biệt trên backpropagation), và thảo luận về các mối quan hệ giữa các mạng thần kinh và các kỹ thuật thống kê thông thường. . | 3. Review of Neural Networks In this chapter we present a brief review of neural networks. After giving some historical background we will review some fundamental concepts describe different types of neural networks and training procedures with special emphasis on backpropagation and discuss the relationship between neural networks and conventional statistical techniques. . Historical Development The modern study of neural networks actually began in the 19th century when neurobiologists first began extensive studies of the human nervous system. Cajal 1892 determined that the nervous system is comprised of discrete neurons which communicate with each other by sending electrical signals down their long axons which ultimately branch out and touch the dendrites receptive areas of thousands of other neurons transmitting the electrical signals through synapses points of contact with variable resistance . This basic picture was elaborated on in the following decades as different kinds of neurons were identified their electrical responses were analyzed and their patterns of connectivity and the brain s gross functional areas were mapped out. While neurobiologists found it relatively easy to study the functionality of individual neurons and to map out the brain s gross functional areas it was extremely difficult to determine how neurons worked together to achieve high-level functionality such as perception and cognition. With the advent of high-speed computers however it finally became possible to build working models of neural systems allowing researchers to freely experiment with such systems and better understand their properties. McCulloch and Pitts 1943 proposed the first computational model of a neuron namely the binary threshold unit whose output was either 0 or 1 depending on whether its net input exceeded a given threshold. This model caused a great deal of excitement for it was shown that a system of such neurons assembled into a finite state automaton could .