In this work, a double gate Junctionless transistor with independent gate operations mimics human behaviors. The front gate with charge trapping in the nitride layer operates as a non-volatile memory, capturing the long-term potentiation (LTP) and depression (LTD). The back gate with single oxide operates as a floating body memory and captures the short-term potentiation (STP) of human behavior. Furthermore, the estimated conductance values are utilized for deep neural networks for image recognition where they are shown achieve 95.37% accuracy for (MNIST) pattern recognition task.