Abstract: Constraints placed on the structure of a conventional multi-layer network consequently enable learning rules to be simplified and the probability of reaching only local minima to be reduced. These constraints include neurons which are either inhibitory or excitatory. Also, for each neuron in the hidden layer, there is at most one synapse connecting it to a corresponding neuron in the output layer. The result is a tree-like structure which facilitates implementation of large scale electronic networks, and allows for parallel training of parts of the network. Additionally, each neuron in the hidden layer receives a reinforcement signal from its corresponding neuron in the output layer which is independent of the magnitude of synapses posterior to the hidden layer neuron. There may be multiple hidden layers, wherein each layer has a plurality of neurons, and wherein each neuron in an anterior layer connects to only one neuron in any posterior layer.

Abstract: Mechanism for triggering the inspiratory phase of a respirator having a three-way connector with an inspiratory conduit and an expiratory conduit, each communicating with the respirator and with a patient communicating conduit. Valve mechanism associated with both the expiratory and inspiratory conduits are automatically operated by a patient attempting to breathe, such that he is only exposed to the air volume in the three-way connector and not to the greater air volume of the respirator and its connected tubing.