Disclosed are systems and methods for performing efficient vector-matrix multiplication using a sparsely-connected conductance matrix and analog mixed signal (AMS) techniques. Metal electrodes are sparsely connected using coaxial nanowires. Each electrode can be used as an input/output node or neuron in a neural network layer. Neural network synapses are created by random connections provided by coaxial nanowires. A subset of the metal electrodes can be used to receive a vector of input voltages and the complementary subset of the metal electrodes can be used to read output currents. The output currents are the result of vector-matrix multiplication of the vector of input voltages with the sparsely-connected matrix of conductances.

A memory device includes a plurality of memory cells and a control unit. The memory cells include a first segment including a resistive memory material for storing information in a plurality of resistance states, a second segment including a non-insulating material, a first terminal, a second terminal, and a third terminal. The first segment and the second segment are arranged in parallel between the first terminal and the second terminal. The control unit is configured to apply in a write mode a write voltage to the first and the second terminal for writing the resistance state, and to apply in a read mode a read voltage to the first and the second terminal for reading the resistance state, and to apply a control signal to the third terminal for adjusting the electrical resistance of the second segment. A related method and control unit are also disclosed.