Recently neural networks have been applied in the context of the signed particle formulation of quantum mechanics to rapidly and reliably compute the Wigner kernel of any provided potential. Important advantages were introduced, such as the reduction of the amount of memory required for the simulation of a quantum system by avoiding the storage of the kernel in a multi-dimensional array, as well as attainment of consistent speedup by the ability to realize the computation only on the cells occupied by signed particles. An inherent limitation was the number of hidden neurons to be equal to the number of cells of the discretized real space. In this work, anew network architecture is presented, decreasing the number of neurons in its hidden layer, thereby reducing the complexity of the network and achieving an additional speedup. The approach is validated on a onedimensional quantum system consisting of a Gaussian wave packet interacting with a potential barrier. K E Y W O R D S machine learning, neural networks, quantum mechanics, signed particle formulation, simulation of quantum systems 1 | INTRODUCTION The aim of quantum chemistry is to understand the properties of matter by modeling its behavior on the scale of assembly of nuclei and electrons.At this scale, the most widely used equation for the interactions between those elements is the Schrödinger's equation. Yet, the exact solution of the Schrödinger equation necessitates exponential need for resources due to increase of the dimensionality of the Hilbert space making such methods intractable for more than a few atoms. [1] The ability to describe systems consisting of thousands of interacting particles requires new highly parallel algorithms running on modern high-performance computers. [2,3] Recently a new formulation of quantum mechanics has been introduced, which does not rely on the standard concept of a wave function but, instead, is based on the new notion of an ensemble of particles provided with a sign. This novel approach is usually referred to as the signed particle formulation of quantum mechanics, [4] while its numerical discretization is known as the Wigner Monte Carlo method. In spite of its relatively recent appearance, it has already been applied to the simulation of a plethora of different quantum systems, in both the single-and many-body cases, showing unprecedented advantages, for example, in the simulation of the hydrogen atom as a full quantum two-body system and thus moving beyond the Born-Oppenheimer approximation, a very promising tool for first-principle-only quantum chemistry. [5] The same approach has also been applied to the study of the resilience of entangled quantum systems in the presence of environmental noise. [6] To the best of the authors knowledge, this is the only formulation of quantum mechanics, which can concretely tackle such problems by means of relatively affordable computational resources and without having to recur to arbitrary unphysical approximations. Despite the unique features of the signed