Suppose you have a neural network with linear activation functions. that is, for each unit the output is some constant c times the weighted sum of the inputs. a. assume the network has one hidden layer. for a given assignment of the weights w, write down equations for the value of the units in the output layer as a function of w and the input layer x, without any explicit mention of the output of the hidden layer. show that there is a network with no hidden units that computes the same function. b. repeat the previous calculation, but this time for a network with any number of hidden layers.

Aheat pump with refrigerant-134a as the working fluid is used to keep a space at 25°c by absorbing heat from geothermal water that enters the evaporator at 500c at a rate of 0.065 kg/s and leaves at 40°c. the refrigerant enters the evaporator at 20°c with a quality of 23 percent and leaves at the inlet pressure as saturated vapor. the refrigerant loses 300 w of heat to the surroundings as it flows through the compressor and the refrigerant leaves the compressor at 1.4 mpa at the same entropy as the inlet. determine: (a) the degrees of subcooling of the refrigerant in the condenser, b)-the mass flow rate of the refrigerant . (c) the heating load and the cop of the pump, and d)-the theoretical minimum power input to the compressor for the same heating load.