Showing papers on "Artificial neural network published in 1976"
TL;DR: A neural network theory is proposed which offers an explanation of many of the facts of classical and operant conditioning and adaptive pattern recognition.
31 citations
ARCO1
TL;DR: Two general methods of analysis of neural nets are developed in terms of elementary matrix algebra, which offer a complete description of the behaviors of neuralnets with relative ease and the special case of two neurons is completely solved.
Abstract: Two general methods of analysis of neural nets are developed in terms of elementary matrix algebra. These methods offer a complete description of the behaviors of neural nets with relative ease. As an example, the special case of two neurons is completely solved. This case may be of interest in the consideration of two interacting quantities of any type, e.g. economic, psychiatric, neuronic, etc.
8 citations
TL;DR: A mathematical model of neural processing is proposed which incorporates a theory for the storage of information that lends support to a distributive theory of memory using synaptic modification.
Abstract: A mathematical model of neural processing is proposed which incorporates a theory for the storage of information. The model consists of a network of neurons that linearly processes incoming neural activity. The network stores the input by modifying the synaptic properties of all of its neurons. The model lends support to a distributive theory of memory using synaptic modification. The dynamics of the processing and storage are represented by a discrete system. Asymptotic analysis is applied to the system to show the learning capabilities of the network under constant input. Results are also given to predict the network's ability to learn periodic input, and input subjected to small random fluctuations.
5 citations
TL;DR: Differential equations, describing time development of local sensitivity and that of ensemble average of firing, are obtained from a digital equation in a neural network such that a slowly varying part of stimulus affects the variation of the averaged firing and its relaxation time non-linearly.
4 citations
TL;DR: Two networks were selected for comparison, one involving visual movement detector interneurons in the locust and the second a hippocampal network in mammals, and approaches toward relating behavior to neural activity were compared in the two networks.
2 citations
1 citations