Recurrent neural circuits

A method comprising:

• providing a computer system, the computer system including at least a processor and a memory, the memory comprising at least an operating system;
• executing a process in the memory, the process comprising:
• providing a recurrent circuit model;
• and converting the recurrent circuit model into a recurrent neural network that can be fit with gradient descent, wherein converting comprises applying a first stage and applying a second stage,
• wherein applying the first stage comprises:
• suppressing feedforward encodings Z by non-negative interactions between units in H[t−1], a feedback gated recurrent unit (fGRU) hidden state from a previous timestep;
• computing suppressive interactions with a kernel WS∈RE×E×K×K wherein E describes a spatial extent of horizontal connections on a single timestep, S is another population of neurons without hidden states, R is a set of real numbers and K is a number of channels of the Kernel;
• convolving the kernel a gated version of a persistent hidden state H[t-1];
• and
• computing a gate activity Gf by applying a sigmoid nonlinearity to a convolution of the kernel UF ∈R1×1×K×K with H[t−1], transforming its activity into the range [0, 1].